Rethinking Indic AI from a Lens of Cultural Heritage Preservation

# Rethinking Indic AI from a Lens of Cultural Heritage Preservation
Source: [https://arxiv.org/html/2607.06544](https://arxiv.org/html/2607.06544)
###### Abstract\.

As Artificial Intelligence \(AI\) makes inroads into different parts of the Indian subcontinent, there is significant interest in studying how AI impacts the linguistic and cultural foundations of this civilization\. AI is seen as a “double\-edged sword” where on the one hand, it can enable access and inclusion for a large population, on the other, it can homogenize worldviews and exclude underrepresented languages and worldviews\. In this paper, we try to characterize this problem by addressing the extensive characteristic nature of Indian linguistics and the way they closely connect to cultural practices and worldview\. We then perform a longitudinal survey of how Natural Language Processing \(NLP\) techniques have evolved in this space, tracing the historical development of Indic NLP, covering key milestones, methodological shifts, and resource creation efforts\. In addition, the paper also examines the structural and sociolinguistic characteristics of Indian languages, such as rich morphology, complex scripts and grammar rules, diglossia, and large dialectal variation, and explains how these create unique challenges for building AI foundation models\. We then discuss the growing role of Indic foundation models and analyze how these models address these long\-standing resource and representation gaps\. Finally, we propose a research direction called ‘Culture Sensing’, which re\-imagines AI based on hermeneutic reasoning\. Culture Sensing aims to address open problems such as ensuring equitable performance across low\-resource languages and producing outputs that are culturally meaningful\. By bringing together past work, current techniques, and emerging trends, this paper outlines research directions that can guide the next phase of Indic NLP and contribute to the development of more robust and inclusive Indic foundation models\.

Indic NLP, Cultural Heritage, Large Language Models, Algorithmic Homogenization, Culture Sensing

††copyright:none††ccs:Computing methodologies Natural language processing††ccs:Applied computing Arts and humanities††ccs:Social and professional topics Computing / technology policy††ccs:Applied computing Digital libraries and archives## 1\.Introduction

Indic languages refer to the wide spectrum of languages spoken in the Indian subcontinent, including India, Nepal, Sri Lanka, Pakistan, Bhutan, Bangladesh, and other countries– that have a long linguistic and cultural history, collectively contributing to more than a fifth of the total world population\. The Indian subcontinent has a long and rich linguistic history, hosting a wide variety of languages\. Each language often uses a different script and has a rich body of literature\. Just in India, the constitution recognizes 22 major literary languages as official languages of the country\. In addition to this, there are about 121 other non\-official, but major languages, and more than 19,000 minor languages, dialects, and creoles\. Languages are also culturally significant across different regions of the subcontinent, often shaping their own unique regional identity\.

An innate hermeneutic diversity can be observed in the case of the Indian subcontinent\. The population of the Indic subcontinent often holds diverse perspectives drawn from the sociocultural discourse\. Figure[1](https://arxiv.org/html/2607.06544#S1.F1)shows pairs of sentences, a source English sentence, and corresponding translations in the Indic languages Hindi and Kannada\. In the first sentence, it can be seen that mentioning of the gender is inevitable while making a statement such as ‘I went to a movie yesterday with my friend’\. From the second sentence, it can be observed that words that signify ‘identity’ rather than ‘ownership’ are used to convey the meaning of owning a house\. Such minute details not only reflect the linguistic divergence but also the underlying hermeneutic differences\.

![Refer to caption](https://arxiv.org/html/2607.06544v1/images/translations.png)Figure 1\.Translated Sentence Pairs Demonstrate the Innate Worldview of the Indic SubcontinentThe integration of AI into the cultural and linguistic landscape of the Indian subcontinent is bound to significantly shape the development and progress of the region\. For India, AI adaptation is driven by a dual necessity: the scope to leapfrog traditional infrastructure deficits\(AIForAll,[2018](https://arxiv.org/html/2607.06544#bib.bib6); Kalyanakrishnan et al\.,[2018](https://arxiv.org/html/2607.06544#bib.bib79)\)and the desire to preserve, scale, and disseminate its immense cultural\(Choudhary and Sukhvir,[2025](https://arxiv.org/html/2607.06544#bib.bib42)\)and linguistic\(Krishna et al\.,[2025](https://arxiv.org/html/2607.06544#bib.bib88)\)diversity\. AI is projected to foster inclusion, economic growth, and also social good\(Maheshwari,[\[n\. d\.\]](https://arxiv.org/html/2607.06544#bib.bib104)\)\. India’s diverse sociocultural fabric can also benefit from using AI for the restoration and preservation of culture and heritage\. It can enhance traditional values likeVasudhaivaKutumbakam\(meaning \- the world is one family\), ensuring focus on inclusive, community\-centric technology\.

Apart from this, improvement in digital literacy and usage has resulted in an increase in Indian language content on the Internet across multiple platforms, including social media, news media, and others\. Technological advances have been penetrating quickly into the Indian population, with the number of Indian language Internet users estimated to exceed 900 million as of the year 2025\(Indian Economy News,[2025](https://arxiv.org/html/2607.06544#bib.bib69)\)\. This advancement calls for language technology that enables people to access information in their native language\.

However, the potential of AI is faced with significant bottlenecks for adoption, primarily due to the digital divide and linguistic challenges\. This is predominantly observed in the current\-day Large Language Models \(LLMs\), that are prone tohomogenizationof hermeneutic interpretations due to lopsided representations of disparate worldviews in their training data, as well as lopsided representation of user base and their feedback that fine\-tunes the model’s responses over time\. The issue is amplified in the case of Indic languages since LLMs are shown to align disproportionately with the linguistic patterns of specific subpopulations\(Sourati et al\.,[2025](https://arxiv.org/html/2607.06544#bib.bib156)\)\. It has also been observed that an individual \(or groups\) exclusively receive negative outcomes in algorithmic decision making\. For example, a job applicant may get rejected from a lot of job opportunities they apply to when all the companies make use of similar resume screening algorithms\(Bommasani et al\.,[2022a](https://arxiv.org/html/2607.06544#bib.bib34)\)\. The major reason for algorithmic bias is the lack of representation for not just Indic language text, but also the diverse worldviews in the Indian subcontinent\. A majority of the LLMs are trained on translations from English language datasets that are collected mostly in urban contexts\. When applied to Indic contexts, they fail to generalize to the different cultural nuances\.

Multiple initiatives have been focusing on Natural Language Processing for Indic languages– or Indic NLP for short, with the goal to build representative datasets in multiple Indic languages, and also to model the different linguistic features of Indic languages\. Indic NLP has its own evolutionary history, somewhat paralleling mainstream research in NLP that is most prominently focused on English, and to a lesser extent, on other European languages\. A considerable amount of research focusing on language technology in Indian languages has been conducted for a long time and is continuously pursued at present\. Research on cultural alignment of LLMs\(Bhagat et al\.,[2026](https://arxiv.org/html/2607.06544#bib.bib13); Agarwal et al\.,[2026](https://arxiv.org/html/2607.06544#bib.bib3)\)is also gaining traction\. These studies have contributed valuable resources, such as a corpus and models, to the Indic NLP community\.

It is important to ensure that both the hermeneutic and linguistic diversity is cohesively preserved\. While there has been substantial development in Indic NLP pertaining to models, datasets, and benchmarks, representation of the multitude of worldviews is still lacking in current\-day language models\. To preserve the cultural diversity in the Indian subcontinent, it is essential to ensure that the corresponding hermeneutic plurality is represented in the models being built\.

In this paper, we present a longitudinal study of research on NLP for Indic languages\. We provide an overview of the evolution of research in this area and the different paradigms explored\. Due to the dynamically changing NLP landscape, we include studies published only till 2025 to the best of our knowledge\. We also investigate prevailing challenges, including the attainment of equitable performance across low\-resource languages and dialects, and the preservation of cultural and linguistic fidelity in generative outputs\.

We also introduce a new research direction,Culture Sensing, that rethinks the framework of AI based on hermeneutic reasoning\. We substantiate this idea with the help of two different use cases where AI techniques are utilized to analyze lesser\-known knowledge systems\. Culture Sensing utilizes the vibrant multimodal knowledge systems in various native communities and represents the corresponding worldview in AI models\. By this, the focus is on making AI models pluralistic and inclusive, thereby preserving lesser\-known knowledge systems on the brink of extinction\. By bringing together foundational research, contemporary methodologies, and emerging trends, this paper sets out strategic research directions intended to facilitate the advancement of robust, culturally inclusive Indic NLP\.

Section[2](https://arxiv.org/html/2607.06544#S2)provides the background of developments in the NLP field and distinguishing features of Indian languages to be considered for building efficient NLP systems\. Section[3](https://arxiv.org/html/2607.06544#S3)reviews different Indic NLP works since their inception till the recent breakthroughs, considering the evolving approaches\. Section[4](https://arxiv.org/html/2607.06544#S4)provides an overview of unique challenges for IndicNLP and discusses mitigation strategies\. Section[5](https://arxiv.org/html/2607.06544#S5)discusses the proposed idea of Culture Sensing to motivate the need for culturally inclusive AI and provides directions towards its achievement\.

## 2\.Characteristics of Indic Languages

Languages in the Indian subcontinent have a rich linguistic heritage and a literary tradition that spans across millennia\. Words in Indic languages have complex morphology, and the grammar for their organization includes elaborate rules\. An understanding of the distinctive features of Indic languages is necessary for building meaningful language technology for them\. This section explores the basic structure and essential features of Indic languages along with examples\.

\{forest\}Figure 2\.Characteristics of Indic Languages### 2\.1\.AksharaSystem of Indian Languages

Indic languages are predominantly phonetic in nature, where the alphabet is based on observing variegated forms of sounds emanating from the human vocal system comprising of throat, tongue, lips and nasal elements\. The alphabet of a majority of Indic languages contains 33 consonants and 15 vowels\. Some languages can also include additional 1\-2 consonants and vowels\. The consonants contain an inherent vowel and are usually divided into 25 structured consonants \(shown in Figure[3\(a\)](https://arxiv.org/html/2607.06544#S2.F3.sf1)\) and the remaining unstructured consonants \(shown in Figure[3\(b\)](https://arxiv.org/html/2607.06544#S2.F3.sf2)\)\. Consonants are further clustered into different segments depending on which part of the human vocal system is used to produce that class of sounds\.

![Refer to caption](https://arxiv.org/html/2607.06544v1/images/structured_consonants.png)\(a\)Structured Consonants
![Refer to caption](https://arxiv.org/html/2607.06544v1/images/unstructured_consonants.png)\(b\)Unstructured Consonants

Figure 3\.Consonants in Indic LanguagesAn individual letter of the alphabet is called anaksharathat consists of a vowel and 0 or more consonants\. Each akshara has its own form and sound\. The letters and words are pronounced exactly as they are written, since the languages are phonetic\. The number of written symbols can be more than the number of characters in the alphabet, as more than one consonant can be combined without an intervening vowel to form digraphs\. Unlike English, where sounds are constructed by lexical concatenation of letters from a base alphabet, Indian languages construct syllables by modifying consonants with verbs and other consonants\.

![Refer to caption](https://arxiv.org/html/2607.06544v1/images/indian-languages.png)\(a\)Different Indic Language Scripts
![Refer to caption](https://arxiv.org/html/2607.06544v1/images/agglutination.png)\(b\)Agglutination Forming Different Words With One Root Word

Figure 4\.Even though the alphabets of Indic languages are similar, the same is not reflected in the scripts used to write them\. The written script has wide variability for different languages in India, as shown in Figure[4\(a\)](https://arxiv.org/html/2607.06544#S2.F4.sf1)\. Differences can be observed even in the structure of graphemes and their combinations\. The rules for the formation of graphemes vary within a script and also across scripts\. For example, the Devanagari script used to write Hindi language includes a horizontal line calledShirorekhaat the top of the word that connects every character of the word\. But this style of writing is not used by every Indic language, and a few of them write graphemes without touching each other\. The alpha syllabic writing system is used, where consonants and vowels are represented as a single unit, as shown in Figure[5\(a\)](https://arxiv.org/html/2607.06544#S2.F5.sf1)\. Consonants represent a letter, while vowels can either appear in atomic form, not connected to consonants, or are dependent on the consonant and marked like a diacritic or some other form of modification\. A vowel can appear to the left, right, top, or bottom of the consonant\. A grapheme representing a combination of vowels is also represented similarly, and the supporting consonant can be a modified form of its original form, or it can be completely different as well\. A large number of diacritics are also present, shown in Figure[5\(b\)](https://arxiv.org/html/2607.06544#S2.F5.sf2)\.

![Refer to caption](https://arxiv.org/html/2607.06544v1/images/vowels.png)\(a\)Letter Formation with Consonants and Vowels
![Refer to caption](https://arxiv.org/html/2607.06544v1/images/diacritic.png)\(b\)Different Diacritics used in Indic languages

Figure 5\.Inherent Features of Indic Languages
### 2\.2\.Formalism of Indian Languages: Panini’s Framework

The formal structures of most Indic languages are either directly based on, or are greatly influenced by the framework established by Panini, called Astadhyayi, written around the6t​h6^\{th\}century BCE\(Bharati and Sangal,[1993](https://arxiv.org/html/2607.06544#bib.bib23)\)\. This framework of structuring language also influences the way language is communicated and characteristics the resultant hermeneutic structures\. In this section, we look at some key elements of the Paninian framework that are seen in almost all Indic languages\.

Morphemesare elemental meaning\-bearing words in Indic languages, that can in turn, be considered to have two elements: thestemand theaffix\. Prefixes, suffixes, circumfuse, and infixes are different types of affixes\. Prefixes precede the stem word, suffixes follow the stem word, and circumfuse morphemes precede and follow the stem word\. Affixes inserted into stem words are called Infixes\. Stem words carry the primary meaning, and affixes give various kinds of additional meaning to the stem word\(Neupane,[2024](https://arxiv.org/html/2607.06544#bib.bib116)\)\.

Among the affixes are a set of case modifiers that are used to assign roles to specific words\. This is enabled with the concept ofkaarakato depict the role of a given word in a sentence\. A set of suffixes calledvibhaktiis usually used to expresskaaraka\. The number ofvibhaktis in a language can be 7 or 8\. This concept can be related to the idea of grammatical cases in languages like English and German\. For example, the wordraja\(king\) can be added with the suffixannuthat representsdwitiyavibhakti to form the wordrajanannuand the correspondingkaarakaaskarma kaaraka, which refers to the object of an action\. Hence, the resultant wordrajanannuforms the object of a sentence it is part of\. These role modifiers give the property offree word orderto Indic languages, where the position of role\-modified words in a sentence can be changed without modifying the overall meaning of the sentence\. The concept ofvibhaktihas to be considered while designing for tasks such as Named Entity Recognition \(NER\) in Indic languages\. It has been observed that the identification of an entity may depend on its suffix corresponding to an appropriatekaarakain the case of the NER task for the Kannada language\(M and Srinivasa,[2023](https://arxiv.org/html/2607.06544#bib.bib103)\)\.

Another concept in Indic languages that gives it an agglutinative nature isSandhior morphophonemic rules that allow a word to be joined with other words or morphemes, resulting in a newly formed word with phonological changes and also possible orthographic variations\. For example, joining the Kannada wordsmane\(house\) andinda\(from\) results inmaneyinda\(from house\) following theAgama sandhi\(Zydenbos,[2020](https://arxiv.org/html/2607.06544#bib.bib173)\)rule\. Compounding orsamaasais also observed frequently\(Kulkarni et al\.,[2012](https://arxiv.org/html/2607.06544#bib.bib90)\)\. Here, two or more meaningful words are joined together to output a \(longer\) word such that its meaning is derived from the underlying words\. The produced word contains more than one stem\. For example, the Sanskrit wordvidyanipuna, meaning one who is sharp in the studies, is formed by two wordsvidya\(education\) andnipuna\(expert\), following theTatpurusha samasarule\. These phenomena not only obscure word boundaries, but also modify the characters at the joining point of the words\. This makes the task of word segmentation and tokenization complex in the case of Indic languages\. Hybrid approaches for word tokenization, such as the one proposed by\(Sandhan et al\.,[2022](https://arxiv.org/html/2607.06544#bib.bib137)\), have demonstrated improved performance using knowledge of the sandhi phenomenon\.

Bharati and Sangal\(Bharati and Sangal,[1993](https://arxiv.org/html/2607.06544#bib.bib23)\)describe a computational grammar formalism for Indian languages in general from Paninian Grammar, which was composed for Sanskrit, with the idea that Sanskrit can form the bridge language for translating between any two Indian languages\. The authors show a compact formalism to parse simple and complex sentences and active and passive voices in sentences using the invariants appearing in verbal and noun parts of the sentence, while the sentence, on the whole, can follow free word order\. The notion of Kaaraka relations is the core of the described Panian Framework\. Kaaraka relations are syntactico\-semantic \(or semantico\-syntactic\) relations that link verbal parts of the sentences to noun parts by invariants appearing with root verbs and nouns in a free\-word order sentence\. The invariants in noun parts are vibhaktis or postpositions, and the invariants of verbal parts are tense\-aspect\-modality \(TAM\) elements\. The invariants help capture the sentence’s gross meaning even when word order is changed\. Moreover, a change in word order conveys secondary information like emphasis, etc\., and does not affect the primary meaning of the sentence\. The verbal group invariant forms impose or demand specific invariants in the noun group, and hence, the verbal group is the demand group, and the noun group is the source group\. The invariants in demand and source are mainly prevalent in the spoken and written texts of Indian languages, which makes the Paninian Framework a suitable formalism for Indian languages\.

There are two components to establishing the kaaraka relations\. The default Kaaraka chart, where three types of kaarakas or nominals, Karta, Karma, and Karana, are mapped to post positions or vibhaktis, and used to establish a relation when the verb group has basic TAM\. The other map is the transformation rules, which map all possible TAMs in the verbal group to specific postpositions in the default kaaraka chart\. One can use the kaaraka relation formalism to build a parser\. The first stage is morphology analysis of a sentence, which involves obtaining grammatical information about words from a lexicon or dictionary and local word grouping of noun groups and verbal groups\. Noun groups contain postposition markers with nouns, and verbal groups contain verbs and their auxiliaries\.

### 2\.3\.Diglossia in Indian languages

Diglossia refers to the difference in the way in which a language is spoken and used in colloquial settings as against the codified, formal variety that is often used in formal education\(Khubchandani,[1985](https://arxiv.org/html/2607.06544#bib.bib85)\)\. This becomes an essential consideration while building language models since the training data for language models mostly belongs to the formal language variety\.

In a majority of Indic languages, the spoken \(colloquial\) style of the language differs significantly from the literary \(formal\) variety\. Multiple dialects of a language exist, and these dialects can also exhibit distinguishing characteristics\. Among multiple dialects, there can be differences in terms of phonology, morphology, lexicon, and syntax\. The distinguishing factor for dialects can be regional or social\. In some cases, the words can be entirely different between dialects\. For example, the word for money isdudduin Bengaluru Kannada, whereas it isrokkain Dharwad Kannada\. Similarly, some dialects of Hindi are Khari Boli, Braj, Bundeli, Marwari, Kumauni, and Garhwali\. Some dialects of languages are also characterized by the community speaking it\. For example, Soliga Kannada is used by the Soliga tribe and has some Tamil influence\. Halakki Kannada is spoken by a tribe called Halakki Vokkaligas\. A few members of the Gowda community living in the Kodagu district of Karnataka use the Arebhashe language\. In addition to this, the inter\-generational tacit knowledge is communicated orally using colloquial style languages, especially in the communities in rural areas\. All of these variations are synchronic, and they occur within a single point in time\.

There also exist diachronic variations, when languages evolve through multiple historical periods\. For example, Kannada language evolved through three periods:Halegannada,Nadugannada, andHosagannada\.Halegannadanurtured classical literature, and most of the popular literature belongs to eitherNadugannadaorHosagannada\. Many phonological variations can be observed between these language varieties\. LLMs can be efficiently used to quantify the diachronic changes as demonstrated by\(Hariharan and Mortensen,[2025](https://arxiv.org/html/2607.06544#bib.bib66)\)\. There is a need for detailed research in this area\.

Language models are generally trained using a corpus that uses a literary style of language\. These language models hence contextually understand the formal style of the language\. However, it’s not necessary that the same model demonstrates similarly when its input is with some dialect or colloquial variety of the same language\. Building models that generalize for dialects is also challenging, as shown for the task of speech recognition in\(Elfeky et al\.,[2018](https://arxiv.org/html/2607.06544#bib.bib59)\), and needs better strategies\. An ideal language model should be inclusive and demonstrate competitive performance for different dialects of the same language\.

## 3\.Historical Context: Evolution of Indic NLP

Different paradigms of NLP have been utilized for processing Indic language data and for building models for Indic languages over time\. The dynamically changing NLP landscape, right from rule\-based processing techniques that used the structure of these languages to form processing rules to the recent transformer architecture, has been experimented with large quantities of data and evaluated for their performance in the case of Indic languages\. We cover the research works on IndicNLP through the different techniques to the best of our knowledge in the following subsections\.

### 3\.1\.Rule\-based Indic NLP

Rule\-based NLP is an approach for processing text using manually crafted, predefined linguistic rules and patterns\. It relies on handcrafted rules built using expert\-defined grammar and dictionaries, and pattern matching using regular expressions to analyze the syntax and semantics\. Although this approach was highly accurate for specific tasks, it was time\-consuming, provided limited generalization, and was rigid\. Early rule\-based IndicNLP works mostly focused on Machine Translation \(MT\), parsing the Indic language text, and building lexical databases such as WordNet for Indian languages\. Table[1](https://arxiv.org/html/2607.06544#S3.T1)provides a comprehensive list of rule\-based Indic NLP models and the tasks they addressed\.

#### 3\.1\.1\.Machine Translation

The MT systems performed Indic\-English, English\-Indic, and Indic\-Indic translation\. Three types of strategies were used for the development of MT systems:

- •Direct translation
- •Interlingua strategy
- •Transfer strategy

The direct translation strategy relied on resources using dictionaries, morphological analysis, and text processing systems for translation involving a specific source and target pair of languages without any intermediate representation\. The transfer strategy first performed text analysis according to the structure of the source language\. Following this, processing in the context of the target language was carried out to perform ’transfer’ at the lexical level, syntactic level, or at the semantic level\. A target language independent universal representation was used by the Interlingua strategy for a given source language text\. Any ambiguities were presumed to be resolved in this representation, and hence it should be usable to generate text in any target language\.

Anglabharti, an English\-Indian language translation system, was proposed by\(Sinha et al\.,[1995](https://arxiv.org/html/2607.06544#bib.bib154)\), which used a rule\-based system using patterns with Context Free Grammar \(CFG\) like structure for the source language \(English\)\. With Hindi as the target language, a prototype system with about 50 rules for English to Hindi translation was reported to be able to translate most of the common sentences\. Another machine translation system, Anusaaraka, proposed by\(Bharati et al\.,[2003b](https://arxiv.org/html/2607.06544#bib.bib15)\)was able to perform translation for the Telugu, Kannada, Marathi, Bengali, and Punjabi to Hindi using human assistance\. For preserving the information while translating from a source language to a target language, substitutibility and reversibility were maintained in the translated strings as explained by\(Bharati et al\.,[2003a](https://arxiv.org/html/2607.06544#bib.bib14)\)\.\(Rao et al\.,[2000](https://arxiv.org/html/2607.06544#bib.bib133)\)proposed a framework for the syntactic transfer of compound complex sentences from English to Hindi using a transfer\-based Machine Assisted Translation \(MAT\) system\. Due to the inflectional nature of Hindi, this work used strategies for inflecting appropriate inflections and case markers as discussed in\(Rao et al\.,[1998](https://arxiv.org/html/2607.06544#bib.bib132)\)\. An interlingua\-based approach for English to Hindi translation was proposed by\(Dave et al\.,[2001](https://arxiv.org/html/2607.06544#bib.bib54)\), using Universal Networking Language \(UNL\) interlingua\. This work investigates the ability of an interlingua\-based approach for translation in handling cross\-language divergences\.

#### 3\.1\.2\.Parsing

In case of parsing, it is observed that the dependency parsing framework is better suited for free\-word order languages, including Indic languages\(Bharati et al\.,[2002a](https://arxiv.org/html/2607.06544#bib.bib17)\)\. This approach was elaborated in an early study by\(Bharati and Sangal,[1990](https://arxiv.org/html/2607.06544#bib.bib22)\)in 1990, which proposed an overall parsing strategy for Indian languages using thekaarakarelations described in Paninian grammar\. This work proposed a parsing system with three components: a morphological analyzer to extract roots of each word in the input sentence, along with other corresponding grammatical information, followed by a Local Word Grouper \(LWG\)\(Bharati et al\.,[1991](https://arxiv.org/html/2607.06544#bib.bib16)\)that formed word groups using information based on adjoining words to reduce the complexity for the core parser\(Bharati and Sangal,[1993](https://arxiv.org/html/2607.06544#bib.bib23)\)\. Dependency parsing analyses the words via the dependency relation between them rather than structuring the phrases hierarchically\. Because of this, dependency analysis is more suited for Indian languages than CFG\.\(Begum et al\.,[2008](https://arxiv.org/html/2607.06544#bib.bib12)\)came up with an approach to perform dependency annotation on Indian languages following the Paninian framework\. This study utilized the concept ofkaarakaas they can be identified syntactically and can be used to understand the underlying semantics\.

An improved performance using data\-driven dependency parsing was obtained by\(Husain et al\.,[2009](https://arxiv.org/html/2607.06544#bib.bib68)\)following a modular cascaded approach in the case of the Hindi language\. In this work, each intermediate layer or module of the parser produced a linguistically valid partial parse\. The final parse obtained using this method aimed at minimizing the adverse effects of long\-range dependency and the non\-projective nature in free word order languages\. The two\-stage approach for parsing was also used by\(Bharati et al\.,[2009c](https://arxiv.org/html/2607.06544#bib.bib21)\)and\(Bharati et al\.,[2009b](https://arxiv.org/html/2607.06544#bib.bib20)\)to propose a constraint\-based hybrid approach for dependency parsing in free word order languages such as Hindi\. This work incorporated hard and soft constraints \(H\-constraints and S\-constraints\) in the two\-stage parsing approach\. H\-constraints, satisfied by any grammatical sentence, include lexical and structural knowledge of the language, such as structural constraints, lexicon, and other language\-specific rules\. S\-constraints, on the other hand, were used as preferences that can be broken by a sentence\.\(Bharati et al\.,[2002c](https://arxiv.org/html/2607.06544#bib.bib24)\)proposed AnnCorra, a dependency\-based tagging scheme for annotating corpora in Indian languages based on the Paninian grammatical model\. The proposed generalized tag scheme aimed at efficiently annotating a corpus and developing treebanks accounting for the distinct syntactic structures in all Indian languages using a tagging scheme made up of notations, defaults, and tagsets\.\(Kanuparthi et al\.,[2012](https://arxiv.org/html/2607.06544#bib.bib80)\)proposed an algorithm for derivational morphological analysis of the Hindi language\. This work utilized an existing inflectional morphological analyzer \(\(Bharati et al\.,[2002a](https://arxiv.org/html/2607.06544#bib.bib17)\)\) for this work\. They used a list of manually extracted derivational suffixes, which were used to form a set of rules for the analyzer, along with a list of words extracted from Hindi Wikipedia\. These components were used by the proposed algorithm to output both inflectional analysis and derivational analysis for a given word\.

#### 3\.1\.3\.Lexical Resource Creation

A rule\-based automatic annotation approach to annotate a Hindi Treebank using the Paninian dependency framework was proposed by\(Gupta et al\.,[2008](https://arxiv.org/html/2607.06544#bib.bib65)\)\. This work extended the experiments in\(Begum et al\.,[2008](https://arxiv.org/html/2607.06544#bib.bib12)\)\. Here, dependency labels were marked only for inter\-chunk relations where a chunk is a set of adjacent words\. The robust formulation of rules for the automatic annotator anticipated a reduction in time and effort for manual annotators in dealing with a large corpus\. A comparison of the annotator with a constraint\-based parser explained in\(Bharati et al\.,[2002b](https://arxiv.org/html/2607.06544#bib.bib25)\)showed that the annotator performed better than the parser for most of the dependency relations\. It was also observed that the annotator helped in improving the results of the first parse of the parser and hence could also be used for post\-processing\.\(Bharati et al\.,[2009a](https://arxiv.org/html/2607.06544#bib.bib18)\)extended this work to include intra\-chunk annotation and included additional linguistic features for better identification of relations\. The parser proposed in this work is a language\-independent engine that takes a rule file for a specific language, as mentioned by\(Gupta et al\.,[2008](https://arxiv.org/html/2607.06544#bib.bib65)\)\.

A subset of the dependency treebank proposed by\(Begum et al\.,[2008](https://arxiv.org/html/2607.06544#bib.bib12)\)was utilized by\(Bharati et al\.,[2008](https://arxiv.org/html/2607.06544#bib.bib19)\)to understand a few of the crucial cues of a language, which are essential for building a robust parser in the case of the Hindi language\. Among the two techniques of dependency parsing, grammar\-driven dependency parsing that rules out those parses that don’t satisfy the established constraints and data\-driven dependency parsing that learns a probabilistic model for parsing, this work experimented with two different data\-driven parsers\. It was observed that the extended feature set for the parser with vibhakti labels increased the performance \(here, vibhakti is a generic term for preposition, post\-position, and suffix\)\. AnnCorra and two more efforts, TransLexGram and Shabda\-Sutra, aimed at creating lexical resources in Indian languages, were discussed by\(Bharati et al\.,[2003c](https://arxiv.org/html/2607.06544#bib.bib26)\)\. Transfer lexicon and grammar, or TransLexGram in short, attempted to produce a transfer lexicon and grammar from English to Hindi\. This work generated bilingual dictionaries, parallel corpora for English\-to\-Indian\-language translation, and simple transfer patterns that can be used directly by machine translation systems\. Shabda Sutra explored the various semantic meanings of a polysemous word\.\(Kulkarni et al\.,[2010](https://arxiv.org/html/2607.06544#bib.bib92)\)proposed a WordNet for Sanskrit\. The WordNet contained verbs in their root forms, following the technique explained in\(Kulkarni and Bhattacharyya,[2009](https://arxiv.org/html/2607.06544#bib.bib91)\)to efficiently store morphological information\.\(Bhingardive et al\.,[2014](https://arxiv.org/html/2607.06544#bib.bib31)\)proposed a semi\-automatic approach to enhance this Sanskrit wordnet, using mapping from an existing bilingual Sanskrit English dictionary and the Princeton WordNet to populate the Sanskrit synsets\.

Table 1\.NLP Research Works using Rule\-based strategy for Indic Languages

### 3\.2\.Corpus\-based Indic NLP

Corpus\-based or statistical NLP relies on the analysis of large, structured corpora to automatically derive linguistic patterns or statistical probabilities\. Corpus\-based NLP uses empirical data to perform tasks such as tagging, parsing, and translation\. Unlike the standard practice that assumes a fixed sentence structure, statistical NLP was used for morphological analysis of the morphologically rich and free word order Indic languages\. Apart from this, research focused on hybrid parsing for Indic languages by integrating rule\-based patterns with statistical models to overcome the drawbacks of the traditional constituency parsing technique\.

In the case of the Statistical Machine Translation \(SMT\), three approaches were used: word\-based, phrase\-based, and hierarchical phrase\-based translation\. While the input sentence was translated word by word and then arranged to get the target sentence in the first approach, each source and target sentence was divided into different phrases and aligned using patterns in the phrase\-based approach\. The hierarchical phrase\-based translation approach used hierarchical phrases with recursive structures instead of simple phrases\. A few studies also combined both rule\-based translation and corpus\-based translation approaches to achieve better results\. In Example\-based translation, the target sentence was formed from the source sentence using pre\-translated examples\. This used parallel corpora, which contained sentence pairs with a source sentence and its translation in the required language\.

Shata\-Anuvadakby\(Kunchukuttan et al\.,[2014](https://arxiv.org/html/2607.06544#bib.bib99)\)was the largest effort at the time and included a collection of phrase\-based Statistical Machine Translation \(SMT\) systems for 110 language pairs\. The study used the Indian Language Corpora Initiative \(ILCI\) parallel corpus of 11 Indian languages, containing roughly 50000 parallel sentences belonging to the health and tourism domains\. An objective of the study was to understand the relation between the accuracy of translation and the language family involved\. It also aimed to explore whether the shared characteristics of Indian languages can reduce the efforts and resources required for building technology\. The provided results called for customized approaches for language family pairs, as the results of translation were better in the case of a few Indic languages, where a higher level of accuracy was seen compared to a few other Indic languages\. Similar results were seen in experiments using increased corpus size, and while the translation performance was better in the case of a few languages, the improvement was minimal for other languages with rich morphology\. The reordering on the source side helped languages such as Tamil, Telugu, Kannada, and Malayalam a little better than languages like Hindi, whereas the post\-editing with transliteration improved the translation quality significantly for the language pairs with scripts derived from theBrahmiscript\.

Incorporation of syntactic and morphological information has been shown to result in significant improvements in phrase\-based SMT\. For English\-Hindi translation, reordering the English source sentence according to Hindi syntax and using a simple suffix separation program for Hindi can be effective\(Ramanathan et al\.,[2008](https://arxiv.org/html/2607.06544#bib.bib129)\)\. In English to Hindi translation, the case markers and suffixes in Hindi are predominantly determined by the combination of suffixes and semantic relations on the English side\. Hence, the challenges posed by features of Hindi, such as free\-word order and rich morphology for translation, are shown to be alleviated by augmenting the aligned corpus of English\-Hindi with the correspondence of English suffixes and semantic relations with Hindi suffixes and case markers\(Ramanathan et al\.,[2009](https://arxiv.org/html/2607.06544#bib.bib128)\)\. Still, translation between language pairs with huge syntactic differences requires re\-ordering, which in turn needs an understanding of the word order in the respective language\. For English\-Hindi translation, research by\(Ramanathan et al\.,[2011](https://arxiv.org/html/2607.06544#bib.bib127)\)demonstrated that the translation quality can be significantly improved by performing clause\-wise translation\.\(Patel et al\.,[2017](https://arxiv.org/html/2607.06544#bib.bib121)\)reported that using rules to transfer the structure of the source sentences before training and translation can lead to a better translation quality\. Additionally, they showed that suffix separation can be used to tackle the morphological divergence between English and highly agglutinative Indian languages\.

Along with the model development efforts, various semantic resources were also created\. A few of them are IndoWordNet\(Bhattacharyya,[2010](https://arxiv.org/html/2607.06544#bib.bib29)\), Bodo Wordnet\(Sarma et al\.,[2010a](https://arxiv.org/html/2607.06544#bib.bib141)\), Tamil Wordnet\(Rajendran et al\.,[2002](https://arxiv.org/html/2607.06544#bib.bib126)\), Kannada Wordnet\(Sahoo and Vidyasagar,[2003](https://arxiv.org/html/2607.06544#bib.bib136)\), Sanskrit Wordnet\(Kulkarni et al\.,[2010](https://arxiv.org/html/2607.06544#bib.bib92)\), Assamese Wordnet\(Sarma et al\.,[2010b](https://arxiv.org/html/2607.06544#bib.bib142)\), and Punjabi Wordnet\(Narang et al\.,[2013](https://arxiv.org/html/2607.06544#bib.bib115)\)\. Other resources, such as n\-grams, were also proposed for Indic languages\(Majumder and Mitra,[2002](https://arxiv.org/html/2607.06544#bib.bib105)\)\.

Multiple approaches for Part\-of\-Speech tagging were also proposed using techniques such as Hidden Markov Model \(HMM\)\(Dandapat et al\.,[2004](https://arxiv.org/html/2607.06544#bib.bib50); Pandian and Geetha,[2008](https://arxiv.org/html/2607.06544#bib.bib119)\)and Maximum Entropy Markov Model \(MEMM\)\(Dalal et al\.,[2006](https://arxiv.org/html/2607.06544#bib.bib48),[2007](https://arxiv.org/html/2607.06544#bib.bib49)\)\. Table[2](https://arxiv.org/html/2607.06544#S3.T2)lists the corpus\-based research works in IndicNLP\.

Table 2\.Research works using the corpus\-based NLP techniques for Indic languagesPaperLanguage\(s\)ApproachParsing\(Dandapat et al\.,[2004](https://arxiv.org/html/2607.06544#bib.bib50)\)BengaliHidden Markov Model\(Singh et al\.,[2005](https://arxiv.org/html/2607.06544#bib.bib151)\)HindiHidden Markov Model\(Dalal et al\.,[2006](https://arxiv.org/html/2607.06544#bib.bib48)\)HindiMaximum Entropy Markov Model\(Dalal et al\.,[2007](https://arxiv.org/html/2607.06544#bib.bib49)\)HindiMaximum Entropy Markov Model\(Gorla et al\.,[2008](https://arxiv.org/html/2607.06544#bib.bib63)\)HindiNormalized Conditional Mutual Information \(NCMI\)\(Pandian and Geetha,[2008](https://arxiv.org/html/2607.06544#bib.bib119)\)TamilHidden Markov Model\(Bharati et al\.,[2009c](https://arxiv.org/html/2607.06544#bib.bib21)\)HindiConstraint based hybrid parsing\(Bharati et al\.,[2009b](https://arxiv.org/html/2607.06544#bib.bib20)\)HindiConstraint based Two\-stage parsing\(V\. et al\.,[2009](https://arxiv.org/html/2607.06544#bib.bib167)\)TamilConditional Random Fields\(Kumar et al\.,[2010](https://arxiv.org/html/2607.06544#bib.bib94)\)SanskritAutomatic segmentation of compounds\(Ramasamy and Žabokrtskỳ,[2011](https://arxiv.org/html/2607.06544#bib.bib131)\)TamilDependency parsingMachine Translation \(MT\) or Transliteration\(Vijayanand et al\.,[2002](https://arxiv.org/html/2607.06544#bib.bib168)\)Bengali, AssameseExample\-based MT\(Ramanathan et al\.,[2008](https://arxiv.org/html/2607.06544#bib.bib129)\)English, HindiUsing syntactic and morphological information\(Ramanathan et al\.,[2009](https://arxiv.org/html/2607.06544#bib.bib128)\)English, HindiUsing case markers and inflections\(Chaudhury et al\.,[2010](https://arxiv.org/html/2607.06544#bib.bib40)\)English, HindiShallow parsing, deep parsing\(Ahsan et al\.,[2010](https://arxiv.org/html/2607.06544#bib.bib4)\)English, HindiCoupling rule\-based and statistical MT\(Visweswariah et al\.,[2011](https://arxiv.org/html/2607.06544#bib.bib170)\)English, Hindi, UrduSource side sentence reordering\(Ramanathan et al\.,[2011](https://arxiv.org/html/2607.06544#bib.bib127)\)English, HindiClause\-based translation with reordering constraints\(Kunchukuttan and Bhattacharyya,[2012](https://arxiv.org/html/2607.06544#bib.bib98)\)MultilingualSource side phrase reordering\(Sankaran et al\.,[2012](https://arxiv.org/html/2607.06544#bib.bib139)\)English, HindiHierarchical phrase\-based MT\(Kunchukuttan et al\.,[2014](https://arxiv.org/html/2607.06544#bib.bib99)\)MultilingualPhrase\-based statistical MT\(Kunchukuttan et al\.,[2015](https://arxiv.org/html/2607.06544#bib.bib100)\)MultilingualParallel transliteration corpora\(Patel et al\.,[2017](https://arxiv.org/html/2607.06544#bib.bib121)\)MultilingualUsing pre\-ordering and suffix separation\(Tholpadi et al\.,[2017](https://arxiv.org/html/2607.06544#bib.bib164)\)MultilingualComparable corpora\-based translation correspondence inductionSemantic Processing\(Reddy et al\.,[2009](https://arxiv.org/html/2607.06544#bib.bib134)\)HindiSemantic category labeling\(Srirampur and Chandibhamar,[2014](https://arxiv.org/html/2607.06544#bib.bib157)\)MultilingualStatistical morphology analysis

### 3\.3\.Indic NLP using Deep Learning

The emergence of Deep Learning \(DL\) revolutionized Indic NLP by moving the focus from manual feature engineering that was common in the statistical NLP era to automatic representation learning\. Characterized by the use of embeddings and attention mechanisms to capture the semantic details that were missed by the previous models, the usage of deep learning models for Indic languages was driven by the need to handle complex morphology, script dissimilarity, and the deficiency of huge parallel corpora for regional language pairs\. Also, the dense vector representation used by these models addressed the issue of the formation of the Out\-of\-Vocabulary \(OOV\) words in Indic languages, often due to inaccurate sub\-word level representation\. DL was used for tasks such as Neural Machine Translation \(NMT\), generating Multilingual representations, and language generation\. Summary of the Indic NLP works using deep learning is provided in Table[3](https://arxiv.org/html/2607.06544#S3.T3)\.

#### 3\.3\.1\.Embedding Representations and Indic Language Models

Pre\-trained embeddings \(monolingual and cross\-lingual\) for 14 Indic languages were generated by\(Saurav et al\.,[2020](https://arxiv.org/html/2607.06544#bib.bib146)\)using both contextual and non\-contextual approaches\. IndicFT\(Kakwani et al\.,[2020](https://arxiv.org/html/2607.06544#bib.bib77)\)developed a set of pre\-trained word embeddings for 11 Indic languages trained on the massive IndicCorp dataset\(Kakwani et al\.,[2020](https://arxiv.org/html/2607.06544#bib.bib77)\)\. The core of IndicFT’s strategy relies on the FastText model, which utilizes character n\-grams \(subword information\) rather than treating whole words as indivisible atomic units\. This method was explicitly chosen because Indian languages are morphologically rich and agglutinative, meaning words often change form with complex suffixes\. By breaking words down into smaller character chunks \(n\-grams\) during training, IndicFT could generate embeddings for rare or unseen words by summing the representations of their sub\-parts, allowing the model to effectively capture semantic similarities between words that share common roots\.

To address the need for robust Natural Language Understanding \(NLU\) across Indic languages, the IndicBERT\(Kakwani et al\.,[2020](https://arxiv.org/html/2607.06544#bib.bib77)\)model was developed using the compact ALBERT architecture trained on the 8\.9 billion token IndicCorp dataset\. Distinct from the character n\-gram approach used in IndicFT, IndicBERT employed a SentencePiece\(Kudo and Richardson,[2018](https://arxiv.org/html/2607.06544#bib.bib89)\)tokenizer with a large shared vocabulary of 200,000 tokens, specifically designed to accommodate the diverse scripts and wide lexical variety of the 12 supported languages \(11 Indian languages plus English\)\. Despite having significantly fewer parameters than massive multilingual baselines like multilingual BERT\(Devlin et al\.,[2019](https://arxiv.org/html/2607.06544#bib.bib55)\)\(mBERT\) and XLM\-R\(Conneau et al\.,[2019](https://arxiv.org/html/2607.06544#bib.bib45)\)\(12M vs\. 110M\+\), IndicBERT demonstrated superior performance on several IndicGLUE\(Kakwani et al\.,[2020](https://arxiv.org/html/2607.06544#bib.bib77)\)benchmark tasks\.

Complementing model development,\(Karthika et al\.,[2025](https://arxiv.org/html/2607.06544#bib.bib81)\)presented a comprehensive intrinsic evaluation of tokenization specifically for 17 Indian languages\. This work contrasted the efficacy of Byte Pair Encoding \(BPE\) and Unigram Language Model \(ULM\), finding that ULM provides superior morphological alignment, adhering more closely to the linguistic segmentation required for morphologically rich and agglutinative Indic languages\. The study further highlighted the critical impact of pre\-processing; tokenizers trained on normalized corpora \(standardizing Unicode and script\-specific characters\) consistently yielded lower fertility scores, indicating significantly more efficient segmentation\. Additionally, they demonstrated that cluster\-based training, grouping languages by typological similarity, significantly reduced the Word Fragmentation Rate \(WFR\) for underrepresented languages compared to joint training strategies, thereby mitigating the dominance of high\-resource languages in the shared vocabulary\.

The design of multilingual vocabularies presents significant trade\-offs\. While IndicBERT adopted a 200k vocabulary to ensure broad coverage,\(Karthika et al\.,[2025](https://arxiv.org/html/2607.06544#bib.bib81)\)observed that increasing vocabulary size from 32k to 256k consistently improves intrinsic metrics such as fertility and fragmentation rate\. However, this work identified a diminishing return in cross\-lingual alignment: vocabulary overlap between languages increased up to 128k but decreased at 256k, suggesting that larger vocabularies may begin to include arbitrary, non\-shared tokens\. Furthermore, the study revealed promising zero\-shot transfer capabilities; multilingual tokenizers trained on high\-resource languages were able to effectively segment unseen, extremely low\-resource dialects like Awadhi, Bhojpuri, and Magahi, achieving fertility scores \(e\.g\., 1\.3–1\.4\) comparable to those of high\-resource languages\.

To address the limitations of massive multilingual models in representing Indian languages,\(Khanuja et al\.,[2021](https://arxiv.org/html/2607.06544#bib.bib83)\)proposed Multilingual Representations for Indian Languages \(MuRIL\), which employs a cased WordPiece vocabulary of 197,285 tokens generated specifically from upsampled Indian language corpora\. Unlike standard multilingual models that often lowercase input, MuRIL preserved case to retain accent information, which is semantically significant in many Indic languages\. The vocabulary generation process explicitly utilized upsampling to ensure that low\-resource languages are adequately represented, preventing high\-resource languages from dominating the subword inventory\.

Empirical analysis demonstrated that MuRIL achieves a significantly lower fertility ratio \(average subwords per word\) across all 17 supported languages compared to mBERT\. High fertility ratios, common in mBERT due to its vocabulary being approximately 78% Latin script, often lead to the over\-fragmentation of Indic words into meaningless characters, thereby degrading semantic understanding\. In contrast, MuRIL allocated a substantially higher proportion of its vocabulary to Indic scripts \(e\.g\., Devanagari, Bengali, Tamil\), ensuring that native words are tokenized into meaningful subword units rather than arbitrary character sequences\. Furthermore, MuRIL addressed the prevalence of code\-mixing and transliteration in the Indian digital landscape by explicitly including transliterated data \(native languages written in Latin script\) during pre\-training\. While mBERT’s vocabulary didn’t provide sufficient coverage for transliterated forms, MuRIL’s tokenizer could effectively recognize and segment transliterated terms, contributing to its superior performance on tasks involving informal text and code\-switching\.

Recent experimental evidence underscores the significant performance advantage of language\-specific pre\-training over cross\-lingual transfer learning for complex morphological tasks\.\(Dasari et al\.,[2023](https://arxiv.org/html/2607.06544#bib.bib52)\)provided a comprehensive evaluation of Telugu morphological analysis and demonstrated that a monolingual Transformer model \(BERT\-Te\), trained from scratch on a dedicated corpus of roughly 8 million Telugu sentences, consistently outperformed massive multilingual baselines including mBERT, XLM\-R, and IndicBERT\. This finding challenges the prevailing assumption that multilingual models are sufficient for low\-resource languages, particularly those with agglutinative morphology\.

The performance gap is most evident in the extraction of fine\-grained grammatical features\. The study reported that the monolingualBERT\-Teachieved an F1 score of 0\.778 for Gender tagging, significantly surpassing IndicBERT \(0\.527\) and XLM\-R \(0\.624\)\. Similarly, for the category of Person, the monolingual model achieved an F1 score of 0\.704, whereas IndicBERT struggled with a score of 0\.475\. The authors attributed this disparity to “concentrated language instruction”; while multilingual models dilute their capacity across hundreds of languages, the monolingual architecture captures the intricate inflectional nuances and structural complexities specific to the target language\. Consequently, for tasks requiring deep morphological understanding, domain\-specific training provides a quantifiable advantage over generalized multilingual representations\.

#### 3\.3\.2\.Sequence Modeling Tasks

Recurrent Neural Networks \(RNNs\), Long Short\-Term Memory \(LSTM\) networks, and Transformer architectures were widely used for handling the sequential nature of text\. These models performed better at ‘remembering’ long\-term dependencies in a sentence compared to the previous modeling approaches\. This capability made them better suited for free\-word order Indic languages\. LSTMs were widely used for POS tagging and Named Entity Recognition \(NER\) tasks\.

POS tagging leveraged multilingual Transformer models to overcome data scarcity\. Addressing the lack of resources for extremely low\-resource languages,\(Kumar et al\.,[2024a](https://arxiv.org/html/2607.06544#bib.bib95)\)presented the first Universal Dependencies \(UD\)\-compliant POS tagging datasets for Angika and Magahi, alongside a new parallel dataset for Bhojpuri\. This work highlighted the critical challenge of sub\-optimal tokenization in multilingual models like MuRIL and XLM\-R, where over\-fragmentation of words in low\-resource languages leads to poor tagging performance\. To mitigate this, this work proposed novel “Look\-back” and “Look\-back\-with\-score” techniques, which utilized the tag of the first sub\-word token or the token with the maximum logit score to represent the entire word\. Experiments demonstrated that Indic\-specific models such as MuRIL outperform massive multilingual models in zero\-shot settings due to reduced language interference, and that cross\-lingual transfer from Hindi is highly effective when alignment errors are minimized\.

Complementing the development of taggers, recent interpretability studies have investigated how transformer models encode POS and morphological properties\.\(Aravapalli et al\.,[2024](https://arxiv.org/html/2607.06544#bib.bib9)\)introducedINDICSENTEVAL, a benchmark for probing linguistic properties across six Indic languages\. Unlike standard tagging tasks, this work utilized POS information \(such as subject/object number and verb attributes\) as diagnostic probing tasks to assess the internal representations of nine multilingual models\. The findings from this study reinforce the superiority of Indic\-specific models \(e\.g\., MuRIL, IndicBERT\) in capturing semantic POS properties compared to universal models\. However, a perturbation analysis revealed a counter\-intuitive insight: universal models \(e\.g\., InfoXLM\(Chi et al\.,[2021](https://arxiv.org/html/2607.06544#bib.bib41)\), mT5\(Xue et al\.,[2020](https://arxiv.org/html/2607.06544#bib.bib172)\)\) often exhibit greater robustness to input noise, such as the dropping of nouns and verbs, suggesting that while Indic\-specific models are more accurate for clean text, they may rely more heavily on specific lexical cues and word order\.

A significant innovation in recent Transformer\-based architectures is the move away from explicit, rule\-based stemming towards “implicit stemming” mechanisms embedded within subword tokenization\.\(Kakwani et al\.,[2020](https://arxiv.org/html/2607.06544#bib.bib77)\)demonstrated this withIndicBERT, a multilingual model pre\-trained on large\-scale corpora spanning 11 Indian languages\. Unlike traditional pipelines that require a dedicated pre\-processing step to strip suffixes using fixed linguistic rules, IndicBERT utilized the SentencePiece tokenizer to decompose words into statistically frequent subword units \(e\.g\., splitting a fused word into root and affix components\)\. This approach allowed the model to learn morphological representations and root\-affix relationships directly from data, effectively bypassing the need for handcrafted stemmers while handling Out\-of\-Vocabulary \(OOV\) terms through subword composition\.

Table 3\.Indic NLP Works using Deep Learning

### 3\.4\.Foundation Models

The development of Natural Language Understanding \(NLU\) for Indic languages has advanced through three distinct phases: initial resource creation, architectural specialization for linguistic nuances, and rigorous, human\-centric evaluation\. This progression is evident across key NLU tasks such as Named Entity Recognition \(NER\), Question Answering \(QA\), Sentence Retrieval, Natural Language Inference \(NLI\), and Paraphrase Detection\.

\(Kakwani et al\.,[2020](https://arxiv.org/html/2607.06544#bib.bib77)\)established the first comprehensive baseline with theIndicNLP Suite\. This work introducedIndicBERTv1 \(an ALBERT\-based model\) and theIndicGLUEbenchmark\. For NER, the model was evaluated on the silver\-standardWikiAnndataset, achieving an F1 score of 64\.47, but trailing the mBERT baseline of 73\.24 due to limited model capacity\. In Question Answering, the suite utilized a cloze\-style multiple\-choice format, where the model achieved an accuracy of 41\.91, demonstrating the feasibility of knowledge extraction in Indic languages\. The work also benchmarked cross\-lingual sentence retrieval using theCVIT\-Mann Ki Baatdataset \(Precision@10: 27\.12\) and introduced coreference\-focused inference via theWinograd NLItask \(Accuracy: 56\.34 on Hindi\)\. Paraphrase detection was evaluated on theAmrithadataset, with the model scoring 93\.11 accuracy on Hindi, setting a strong initial precedent for classification tasks\.

Addressing the limitations of general multilingual models,\(Khanuja et al\.,[2021](https://arxiv.org/html/2607.06544#bib.bib83)\)introducedMuRIL, a BERT\-based model augmented with translation and transliteration data to handle code\-mixing and script diversity\. This specialization led to state\-of\-the\-art results on theXTREMEbenchmark\. In NER,MuRILachieved an F1 score of 77\.2, significantly outperforming global baselines like mBERT and XLM\-R on structural tasks\. For Question Answering, it demonstrated superior reading comprehension on extractive datasets likeXQuAD\(Hindi F1: 73\.9\) andTyDiQA\(Avg F1: 75\.4\)\. The model also excelled in cross\-lingual tasks, achieving high accuracy in Natural Language Inference \(IndicXNLI: 74\.1\) and Paraphrase Detection \(72\.4\), leveraging its transliteration\-aware pretraining to bridge semantic gaps across languages\.

The most recent phase, led by\(Doddapaneni et al\.,[2023](https://arxiv.org/html/2607.06544#bib.bib58)\), prioritized evaluation integrity with theIndicXTREMEbenchmark\. This work introducedIndicBERTv2, trained on the massiveIndicCorpv2\. A key shift was the use of human\-verified datasets likeNaamapadamfor NER, whereIndicBERTv2 scored 72\.4, beating global baselines but trailingMuRIL\. In Question Answering, the model matched the strongMuRILbaseline on the manually curatedIndicQAdataset \(F1: 47\.7\) while vastly outperforming XLM\-R\.IndicBERTv2 showed its strongest gains in Sentence Retrieval, scoring 69\.4 on the high\-qualityFLORESdataset, a 14\.5\-point improvement over prior models\. However, in ”strict” semantic tasks like Paraphrase Detection on the newIndicXParaphrasedataset, it scored 56\.9, again highlighting that while larger corpora improve general alignment, specific pretraining strategies remain crucial for resolving fine\-grained semantic nuances\.

Bharat Parallel Corpus Collection \(BPCC\), the largest publicly available parallel corpus for Indic languages, was created by\(Gala et al\.,[2023](https://arxiv.org/html/2607.06544#bib.bib60)\)\. In addition to this, the work also introduced an n\-way parallel benchmark covering 22 Indian languages, featuring diverse domains, Indian\-origin content, and source\-original test sets\.IndicTrans2, the first model to support all 22 languages, was also created as a part of this work\. The lack of parallel training data, robust benchmarks, and translation models spanning all 22 languages was overcome with this work\.

#### 3\.4\.1\.Indic NLP using Generative AI

Recently, several groups have been leading efforts to build generative LLMs that cater to the diverse linguistic landscape of India\. A few notable initiatives are Sarvam AI111https://www\.sarvam\.ai/, BharatGen222https://bharatgen\.com/, and AI4Bharat333https://ai4bharat\.iitm\.ac\.in/among others\.

BharatGen has introduced pioneering works, including\(DocBodh,[2025](https://arxiv.org/html/2607.06544#bib.bib57)\)\- a GenAI suite for Indic Document understanding,\(Param,[2025](https://arxiv.org/html/2607.06544#bib.bib120)\)\- a text model trained on India\-centric data, and can understand and generate human\-like text in multiple Indian languages and dialects\. Sarvam AI has released powerful models, including\(Sarvam\-M,[2025](https://arxiv.org/html/2607.06544#bib.bib144)\)\- a multilingual, hybrid\-reasoning, text\-only model built on Mistral\-Small444https://mistral\.ai/news/mistral\-small\-3\-1, following Sarvam\-1 \- a language model with 2\-Billion parameters specifically optimized for Indian languages\. Other noteworthy models are\(Sarvam Translate,[2025](https://arxiv.org/html/2607.06544#bib.bib145)\)\- providing comprehensive coverage of all scheduled Indian languages with formal translation style, and\(Mayura,[2025](https://arxiv.org/html/2607.06544#bib.bib111)\)\- designed to convert text between English and Indian languages while preserving meaning and context\.

In addition to this, initiatives such as Bhashini555https://bhashini\.gov\.in/are launched by the government with an aim to bridge the language gap and enable access to digital services and content in regional languages\. Bhashini provides translation services across more than 36 languages and also hosts a unified hub666https://bhashini\.gov\.in/vatikameant for discovering, exploring, and contributing AI models and datasets tailored for India’s diverse linguistic \- technological scenario\.

The development of foundation and instruction\-tuned models for Indic languages has accelerated since late 2023\. Some of them are Gajendra\(AI,[2024](https://arxiv.org/html/2607.06544#bib.bib5)\), Airavata\(Gala et al\.,[2024](https://arxiv.org/html/2607.06544#bib.bib61)\), Krutrim LLM\(Kallappa et al\.,[2025](https://arxiv.org/html/2607.06544#bib.bib78)\), Tamil Llama\(Balachandran,[2023](https://arxiv.org/html/2607.06544#bib.bib10)\), Bharat GPT\(CoRover\.ai,[2024](https://arxiv.org/html/2607.06544#bib.bib46)\), and Navarasa\(Lab,[2024](https://arxiv.org/html/2607.06544#bib.bib101)\)\. Table[4](https://arxiv.org/html/2607.06544#S3.T4)lists the generative AI works using Indic languages\.

The training datasets for prominent Indic language models and initiatives often come from a combination of large\-scale web scraping, synthetic data generation\(Manoj et al\.,[2025](https://arxiv.org/html/2607.06544#bib.bib108)\), curated translation pairs\(Karthika et al\.,[2026](https://arxiv.org/html/2607.06544#bib.bib82)\), and crowdsourced speech\(Javed et al\.,[2024](https://arxiv.org/html/2607.06544#bib.bib74); Bhashadaan,[2025](https://arxiv.org/html/2607.06544#bib.bib27)\)\. To the best of our knowledge, the representation of knowledge from indigenous communities is little when compared to that from the conventional sources\. Directions towards bridging this gap are discussed in Section[5](https://arxiv.org/html/2607.06544#S5)\.

Table 4\.Indic NLP Foundation Models

### 3\.5\.Speech Recognition for Indic Languages

Table 5\.Key Projects and Models in Indic ASRResearch in Automatic Speech Recognition \(ASR\) for Indic Languages has achieved significant progress, paralleling the works in NLP with large foundational models like Whisper\(Radford et al\.,[2022](https://arxiv.org/html/2607.06544#bib.bib125)\)\. ASR faces similar challenges to the ones explained in Section[4](https://arxiv.org/html/2607.06544#S4)in addition to code mixing\(Thara and Poornachandran,[2018](https://arxiv.org/html/2607.06544#bib.bib163)\), multilingual speech, and noisy recording\. Table[5](https://arxiv.org/html/2607.06544#S3.T5)lists the recent works in ASR for Indic languages in brief\.

A critical bottleneck identified in recent studies for Indic ASR is the tokenization process, which disproportionately impacts low\-resource languages compared to others\. While high\-resource languages benefit from extensive token sets in pre\-trained models, low\-resource languages suffer from limited vocabulary coverage\. This deficiency forces the tokenizer to fragment words into numerous small subwords or characters, leading to increased sequence lengths and substantially slower auto\-regressive inference speeds\. To address these inefficiencies,\(Tripathi et al\.,[2025](https://arxiv.org/html/2607.06544#bib.bib165)\)proposed a novel tokenization strategy that augments the existing Whisper vocabulary with language\-specific Byte Pair Encoding \(BPE\) tokens\. These tokens were derived from datasets representative of common Indian language sequences to reduce token fertility\. The pre\-trained model architecture was modified by expanding the dimension of the final token head layer, initializing new random weights for the added tokens while freezing the original weights to preserve multilingual capabilities\.

Through ablation studies, an optimal threshold of 250 additional tokens per language was identified\. This targeted vocabulary expansion significantly compressed token sequences; for example, token counts for Hindi and Malayalam sentences were reduced by approximately 30% and 60%, respectively\. Empirical evaluations demonstrated that this reduction not only accelerated inference speeds outperforming optimized baselines but also consistently improved the Word Error Rate \(WER\) across model variants\.

While these Indic ASR models are increasingly capable of addressing cultural nuances, they are far from being robust\. Substantial progress is still required to bridge the gap between the performance in mainstream languages and the real linguistic diversity\. The focus of future research must be on curation of representative datasets and design of models that inherently capture the regional variations, rather than fixing them into rigid, monolingual frameworks\. A low\-cost and easy\-to\-implement approach for ASR using colloquial speech is discussed in Section[5\.2\.1](https://arxiv.org/html/2607.06544#S5.SS2.SSS1)\.

## 4\.Challenges for Indic NLP

While Indic NLP research has made significant progress in recent times, persistent challenges pose challenges for building representative and inclusive language models for Indic languages\. These challenges exist in the case of a majority of Indic languages and also other related languages, and are not observed in languages like English, which are used to build mainstream NLP systems\. In this section, we discuss these challenges in detail and also discuss relevant research works that focused on finding solutions using specific cues such as the structure of Indic languages, the difference between dialects, etc\.

\{forest\}Figure 6\.Main Challenges for Research in Indic NLP### 4\.1\.Complex Morphology and Grammar Rules

Some of the distinct features of morphology and grammar in the case of Indic languages, such as thekaarakarules along with the free word order, pose significant challenges when it comes to building language models for these languages\. While there is a growing social and commercial need for the availability of language technologies in Indic languages, the scale and diversity of these languages make the design of inclusive language models difficult\. Additionally, a few of the language features also need elaborate modeling\. For example, compound verbs are verb\-verb collocations where the polar verb adds the semantics and the vector verb acts as a modifier\(Slade,[2016](https://arxiv.org/html/2607.06544#bib.bib155)\)\. Processing a sentence with such verbs requires a computational model to acquire both morphological and pragmatic understanding\. Building language models that can understand and represent such fine nuances with precision is a complex task\.\(Bhattacharyya et al\.,[2019](https://arxiv.org/html/2607.06544#bib.bib30)\)discussed a list of challenges for Indic language computing and suggested some pointers for overcoming them\. A few of the proposed solutions are a unified representation of Indic languages using a superset of sounds, interactive crowd sourcing for resource creation, and generic acoustic models and generic language models across various languages\. In this section, we discuss the related studies that focus on using NLP techniques to model the linguistic features of Indic languages\.

Indic languages are highly inflectional, and one root word can have multiple morphological variants\. The agglutinative nature also makes morpheme boundaries hard to distinguish\. Even though a set of rules can be used to identify the stem of a given word, this process requires linguistic expertise, is time\-consuming, and language\-specific\. Researchers have explored the application of corpus\-based techniques for morphological processing\.\(Kulkarni and Srinivasa,[2013](https://arxiv.org/html/2607.06544#bib.bib93)\)proposed an improved indexing technique for identifying grammatically modified versions of the same root word\. A fuzzy matching\-based indexing mechanism inspired by prefix trees was used to index and retrieve different morphological forms of a term\. This solution can be adapted for other similar languages with minimum modifications due to the similarities in their Unicode encoding and morphological behaviors\. Another study by\(Bhat,[2012](https://arxiv.org/html/2607.06544#bib.bib28)\)found unsupervised morphological segmentation algorithms to perform well for the problem of morpheme boundary detection in Kannada\.\(Ramanathan and Rao,[2003](https://arxiv.org/html/2607.06544#bib.bib130)\)proposed a domain\-independent and computationally inexpensive stemmer for the Hindi language\. A suffix list was developed and used in this work\. In the case of the Bengali language,\(Majumder et al\.,[2007](https://arxiv.org/html/2607.06544#bib.bib106)\)explored the clustering\-based approach, where equivalence classes of root words and their morphological variants were identified from a lexicon using string distance measures\. Stemming performance using the approach provided results comparable to the standard rule\-based stemmers and was observed to be effective for languages that are primarily suffixing\. Unsupervised learning for acquisition of morphological knowledge from a text corpus was experimented with by\(Sharma et al\.,[2008](https://arxiv.org/html/2607.06544#bib.bib148)\)for the Assamese language\. This approach was used to build a lexicon and subsequently used for morphological analysis\. A formulation for derivational morphology, augmented Finite State Automata, was proposed along with a formalism for a lexicon writer for specifying a lexicon by\(Sengupta and Chaudhuri,[1996](https://arxiv.org/html/2607.06544#bib.bib147)\)\. This approach was also proposed to be useful as a building block for a spelling corrector in the case of the Bangla language\. A finite state machine was used to develop a prototype morphological analyzer for the Kannada language\(Vikram and Urs,[2007](https://arxiv.org/html/2607.06544#bib.bib169)\)\.

Efficient morphological processing along with syntactic cues significantly improved the overall performance when incorporated into tasks such as SMT\(Ramanathan et al\.,[2008](https://arxiv.org/html/2607.06544#bib.bib129)\)and data\-driven dependency parsing\(Ambati et al\.,[2010](https://arxiv.org/html/2607.06544#bib.bib7); Malladi and Mannem,[2013](https://arxiv.org/html/2607.06544#bib.bib107)\)\. Another study found that augmenting the phrase table with all possible forms of a verb can improve the overall accuracy of a phrase\-based MT system in the case of highly inflected languages\(Gandhe et al\.,[2011](https://arxiv.org/html/2607.06544#bib.bib62)\)\. Morphological analysis has also been integrated with the task of tagging in multiple studies\. Using a stemmer along with a morphological analyzer,\(Shrivastava et al\.,[2005](https://arxiv.org/html/2607.06544#bib.bib149)\)performed Part\-of\-Speech \(POS\) tagging in the Hindi language\.\(Shrivastava and Bhattacharyya,[2008](https://arxiv.org/html/2607.06544#bib.bib150)\)showed that an HMM\-based POS tagger was able to achieve reasonably good accuracy when stemming was performed as pre\-processing\. To overcome the lack of standardized tagsets,\(Sankaran et al\.,[2008](https://arxiv.org/html/2607.06544#bib.bib138)\)proposed a common POS tagset hierarchical framework for eight Indic languages\.

### 4\.2\.Diglossia

Most of the Indic NLP applications focus on the formal language varieties\. Along with this, the corpora used for training of Indic LLMs are dialect\-neutral\. Studies are being conducted to model the relation between the formal variety of a language and its dialects\.\(Mishra and Bali,[2010](https://arxiv.org/html/2607.06544#bib.bib113)\)listed rules for phonology transfer from standard Hindi to a number of its prominent dialects, Bundeli, Bagheli, Kanauji and Awadhi\. For Punjabi language and its dialects, Malwai and Doabi, a conversion system was proposed by\(Singh and Singh,[2015](https://arxiv.org/html/2607.06544#bib.bib152)\)using bilingual dictionaries and morphological conversion rules\. In the case of the Tamil language, an approach for conversion from spoken dialectal language to standard written Tamil utilized Finite State Transducer \(FST\)\(Marimuthu and Devi,[2014](https://arxiv.org/html/2607.06544#bib.bib110)\)\. A framework for capturing synchronic variation by modeling the underlying diachronic variation was proposed by\(Choudhury et al\.,[2006](https://arxiv.org/html/2607.06544#bib.bib44)\)\. This work used an ordered set of rewrite rules representing phonological changes that occurred during the evolution of dialects to derive current dialectal forms of the Bangla language from their classical counterparts\.

Corpora collected in informal settings with unscripted, impromptu conversations can reveal the vibrant nature of languages and also reveal their characteristic patterns\(Dash and Chaudhuri,[2001](https://arxiv.org/html/2607.06544#bib.bib53)\)\. Human in the loop approach can be helpful in collating dialect\-rich corpus from informal sources as shown by\(Srivatsa et al\.,[2024](https://arxiv.org/html/2607.06544#bib.bib160)\)\. This work utilized a small speech corpus collected from a rural community radio to build a colloquial text corpus\. With the widespread availability of language models, there is a growing need to build dialect\-rich corpora that can be used in turn to incorporate diverse knowledge into the language models\.

### 4\.3\.Lack of Resources

The lack of resources in Indic NLP refers to the multifaceted scarcity that spans data, computation, and linguistic expertise\. While the Indian subcontinent is data\-rich in terms of human interactions and knowledge systems, the digital footprint is disproportionately small compared to English\. LLMs primarily rely on large amounts of high\-quality data along with rich representations in the form of word embeddings\. These word embeddings capture the contextual semantics of words and tokens, and are learned from huge text corpora with millions of words\. However, the availability of such huge datasets in the case of Indic languages is limited, and this presents a challenge for the development of Indic language technologies\. The largest publicly available Indic language datasets are of the order of billions of tokens777[https://huggingface\.co/datasets?language=language:hi&sort=largest](https://huggingface.co/datasets?language=language:hi&sort=largest), whereas it is much higher for languages like English\. Also, Indic languages have adopted multiple different encoding standards, such as ISCII\(Indian Script Code for Information Interchange,[2009](https://arxiv.org/html/2607.06544#bib.bib70)\), Unicode\(UNICODE STANDARD For Indic Scripts,[\[n\. d\.\]](https://arxiv.org/html/2607.06544#bib.bib166)\), and font standards like ISFOC\(ISFOC Standard for Fonts,[\[n\. d\.\]](https://arxiv.org/html/2607.06544#bib.bib71)\)\. These multiple standards have different software dependencies, and hence, uniform adaptation becomes difficult\. In addition to this, there is no standard for transliteration among Indic languages and from Indic languages to other languages\. Studies have proposed multiple approaches for Indic language transliteration\(Kunchukuttan et al\.,[2015](https://arxiv.org/html/2607.06544#bib.bib100); Srivastava and Bhat,[2013](https://arxiv.org/html/2607.06544#bib.bib158); Diwakar et al\.,[2010](https://arxiv.org/html/2607.06544#bib.bib56); Joshi et al\.,[2018](https://arxiv.org/html/2607.06544#bib.bib76); Surana and Singh,[2008](https://arxiv.org/html/2607.06544#bib.bib162)\)\. However, there can still be variation in the representation of words\. For example, the word for ’Thank you’ in Hindi can be written asdhanyawad,dhanywad,dhanyavad, ordhanyvad\. Large, labeled corpora are critically needed for Indic languages, and active research efforts are underway to address this gap\.

Enabling Minority Language Engineering \(EMILLE\)\(McEnery et al\.,[2000](https://arxiv.org/html/2607.06544#bib.bib112)\), Linguistic Data Consortium for Indian Languages \(LDC\-IL\)\(Choudhary,[2021](https://arxiv.org/html/2607.06544#bib.bib43)\)are a few of the initiatives aimed at creating a corpus in Indic languages\. Studies have also experimented with various approaches to overcome the lack of data\. For the task of translation,\(Philip et al\.,[2021](https://arxiv.org/html/2607.06544#bib.bib123)\)used iterative alignment to provide a large\-scale sentence\-aligned dataset using publicly available websites such as press releases by the government\. For translation between Assamese and other Indic languages, a comparison between statistical and neural MT was made by\(Baruah et al\.,[2021](https://arxiv.org/html/2607.06544#bib.bib11)\)to improve the translation performance in the case of the Assamese language\.\(Kumar et al\.,[2024b](https://arxiv.org/html/2607.06544#bib.bib96)\)contributed a Universal Dependency compliant parallel dataset for POS tagging in three Indic languages\- Angika, Magahi, and Bhojpuri\. Submissions to the low\-resource Indic language translation task as part of the Conference on Machine Translation \(WMT\)\(Pakray et al\.,[2025](https://arxiv.org/html/2607.06544#bib.bib117)\)revealed important insights\. A few of them are\-

1. \(1\)a strong correlation exists between translation performance and the data size
2. \(2\)the effect of data quality and model optimization can outbalance the data quantity
3. \(3\)asymmetry in translation quality from one direction to the other
4. \(4\)models that perform well on one metric also perform well on other metrics of translation quality

The shared linguistic features of Indic languages have also been useful in building language resources for low\-resource languages\. Studies have utilized resources of a related language with more resources to overcome the limitations for low\-resource languages\(Singh et al\.,[2008](https://arxiv.org/html/2607.06544#bib.bib153)\)\. The similarity in scripts and sentence structure is shown to be effective in building language models for low\-resource languages\(Khemchandani et al\.,[2021](https://arxiv.org/html/2607.06544#bib.bib84)\), rather than direct training or using English as the pivot language\. Even for translation, it is found that using a parent multilingual neural MT model and fine\-tuning it on a low\-resource language pair of interest performs better than standard neural MT\(Goyal et al\.,[2020](https://arxiv.org/html/2607.06544#bib.bib64)\)\.

Apart from the data quantity standpoint, the lack of specialized resources for Indic languages leads to technical inefficiencies\. The issue of subword fragmentation, where a standard tokenizer breaks a single word into multiple tiny, meaningless fragments, is very much relevant in the case of Indic languages\. This causes an increase in computation cost and latency\. Hence, an English sentence with ‘n’ tokens might have significantly more than fragments in the case of the Indic languages, also making it slower, more expensive, and meaningless\. An approach was proposed by\(Brahma et al\.,[2025](https://arxiv.org/html/2607.06544#bib.bib36)\), incorporating sandhi splitting to enhance the subword tokenization\. It was shown that handling dependent vowels by forming a cohesive unit with other characters instead of occurring as a single unit leads to a reduction in fertility scores while maintaining performance in the language modeling task\.

Techniques such as cross\-lingual transfer\(Pawar et al\.,[2023](https://arxiv.org/html/2607.06544#bib.bib122)\)and back\-translation\(Das et al\.,[2025](https://arxiv.org/html/2607.06544#bib.bib51)\)have been adapted to mitigate the data scarcity issue\. Crowd\-sourcing initiatives like Bhashadaan888[https://bhashadaan\.bhashini\.co\.in/bhashadaan/en/home](https://bhashadaan.bhashini.co.in/bhashadaan/en/home)are working on manually collecting data to train and to empower the linguistic diversity in Indic languages\.

## 5\.Language and Culture

Sections[3](https://arxiv.org/html/2607.06544#S3)and[4](https://arxiv.org/html/2607.06544#S4)outlined the historical evolution and predominant challenges of Indic NLP, translating these insights into pluralistic AI requires new conceptual frameworks\. To nudge the field to move forward, we proposeCulture Sensing\- the process of understanding the worldviews and hermeneutics of a population to conduct meaningful communication with them, and also to enrich our own understanding of the world\. Culture Sensing seeks to gather knowledge from various native discourses, regardless of the medium used, such as speech, text, and more\. Unscripted, spontaneous data curation techniques are preferred to emphasize authenticity\. The focus is on preserving the numerous credible hermeneutic schools and their associated methods of inquiry, as well as enhancing foundation models accordingly\. In this section, we discuss the relation between language and culture, and how the inherent worldview in foundation models reflects the underlying culture\. We also provide a demonstration of the Culture Sensing approach reflected in two different applications\.

Language and Culture have a synergistic relation\. Language acts as the primary vehicle through which cultural values, histories, and social systems are conserved and communicated\. This relationship is complex in the context of the Indian subcontinent due to the immense linguistic diversity and vibrant cultural heritage\. Language mirrors the intricate social structures and value systems in this region\. For example, Hindi wordsTu,Tum, andAapall mean ‘you’, but refer to distinct levels of formality or relationship\. The cultural emphasis on family structures is also clearly visible in the language usage\. For example, a majority of the Indic languages have distinguishing names for paternal uncle and maternal uncle\. A few of the concepts precisely elaborated in Indic languages, such asDharmaandKarmacarry inherent philosophical ideas and are untranslatable into non\-Indic languages without significant loss of meaning\. The powerful connection between culture and language has also influenced political boundaries \(Karnataka state for Kannada language speakers, Tamil Nadu for Tamil language speakers\), and different linguistic groups share a unique cultural legacy and literary tradition\. A majority of the subcontinent’s history, in the form of folklore, oral epics, and proverbs, is preserved through intergenerational transmission\. These oral traditions are prone to being erased when the corresponding dialect ceases to exist\.

In recent times, English serves as a lingua franca and has been intertwined such that ‘Indian English’ incorporates the local syntax and loanwords\. The common practice of code\-switching \(Hinglish, Kanglish\) represents a modern hybrid identity that combines traditional values with global influences\. It can be said that a language expresses the collective beliefs, perceptions, and value systems held by the members of the same social group, which constitute the culture of that society\. With the rapid adaptation of LLMs to different language processing tasks, it is essential to inquire into the underlying cultural representation\.

Foundation Models have demonstrated exceptional performance in language generation and reasoning, open\-ended question answering, and multimodal understanding\. While LLMs are applied across a broad range of verticals, it is necessary to understand the extensive societal consequences they entail\. The paradigm shift in AI brought about by LLMs also comes with intrinsic biases such as misrepresentation, underrepresentation, and overrepresentation, and extrinsic harms that can be representational harms, abuse, and performance disparities\(Bommasani et al\.,[2022b](https://arxiv.org/html/2607.06544#bib.bib35)\)\. The downstream applications created by fine\-tuning the foundation models have often displayed performance disparity in the case of minority social groups\(Blodgett and O’Connor,[2017](https://arxiv.org/html/2607.06544#bib.bib33); Koenecke et al\.,[2020](https://arxiv.org/html/2607.06544#bib.bib86)\)\.

Linguistic homogenization can be clearly identified in LLM\-assisted writing\. AI\-enabled writing assistants have been linked to reduced linguistic diversity and alteration of individual stylistic elements while amplifying dominant characteristics or biases\(Sourati et al\.,[2025](https://arxiv.org/html/2607.06544#bib.bib156)\)\. Repeated usage of such assistants can result in normalized grammar, simplification of dialects, and erosion of sociolinguistic markers in writing\. LLMs have also been shown to erase culturally specific linguistic markers while retaining the semantic meaning, especially in professional writing\(Kumar Navneet et al\.,[2026](https://arxiv.org/html/2607.06544#bib.bib97)\)\.

LLMs also often demonstrate cultural homogenization, where they internalize dominant cultural assumptions such as the prioritization of Western values, usage of internet slang, and globally dominant political views\. A cross\-cultural study\(Agarwal et al\.,[2025](https://arxiv.org/html/2607.06544#bib.bib2)\)with participants from India and the United States showed that AI models such as writing assistants homogenize writing towards Western norms, decreasing subtle cultural differences\. This study showed that among the two groups, Indians were more likely to write like Americans while using AI assistants, but they needed to put more effort than Americans to gain a similar productivity boost\. Here, AI doesn’t just change the written content but also the more internalized elements of cultural expression\. Language models are also prone to follow similar writing styles and similar ‘neutral’ tones, and can underperform\(Marco et al\.,[2024](https://arxiv.org/html/2607.06544#bib.bib109)\)when used for creative writing tasks\. Contrasted with the rich oral storytelling traditions with non\-linear, layered components, LLMs follow a similar structure almost all the time\. It can be said that homogenization is circular; lack of diversity in model training leads to lack of diverse outputs, which in turn guides the user expectations and standards\.

The lack of cultural, epistemic, and linguistic inclusivity in LLMs is alarming\. While these models are being used in different domains, including education, technology, healthcare, etc\., the inherent narrative or worldview in these LMs should be understood in\-depth\. Especially for the Indian subcontinent, with thousands of language dialects and grouped multilingual identities, it is essential to represent the diversity in the AI ecosystem\. In this section, we discuss how the language used to train the LLMs can be used to understand the embedded cultural cues\.

### 5\.1\.Worldview of LLMs

A majority of the LLMs are trained using data extracted from conventional sources, including Wikipedia, news websites, and other publicly available datasets\. For example, mBERT is trained on Wikipedia articles of the top 100 languages with the largest Wikipedia\.999https://github\.com/google\-research/bert/blob/master/multilingual\.md\#data\-source\-and\-samplingThese datasets sourced from such mainstream platforms are widely available as labeled gold standard corpora and are frequently used as benchmark datasets\. Otherwise, extracting good\-quality training corpora followed by relevant processing and labeling for the corresponding downstream task or domain is an expensive task\. It requires sufficient time, computational resources, and annotators with linguistic knowledge for hand\-labeling the dataset\. As a result of this, a majority of the training and fine\-tuning experiments are dependent on a very few public datasets that were built either by crowdsourcing or by specific vendors\. This is likely to lead to standardization of algorithms due to more and more language models being trained on data from similar sources, finally leading to homogenization of the model outputs\(Creel and Hellman,[2022](https://arxiv.org/html/2607.06544#bib.bib47)\)\. Language models that are trained on snapshots of the internet are more likely to mimic the views of crowd workers who were involved in the creation of data\. These LMs have the least representation for a few demographic groups \(for example, senior citizens, people without a college degree\) that were excluded from the crowd sourcing process\(Santurkar et al\.,[2023](https://arxiv.org/html/2607.06544#bib.bib140)\)\. A likely outcome of this can be that a social group with minimal representation in the dataset might be isolated in the language model system\.

The LLMs fine\-tuned with human feedback are often seen demonstrating a worldview aligned to a particular group of people in response to subjective queries\. A response from these models contains an embedded narrative, and it can be of great influence when used in information retrieval and decision\-making tasks\. For example, when it comes to political ideology, Chat GPT has expressed left\-libertarian aligned views\(Hartmann et al\.,[2023](https://arxiv.org/html/2607.06544#bib.bib67); Motoki et al\.,[2023](https://arxiv.org/html/2607.06544#bib.bib114); Ceron et al\.,[2024](https://arxiv.org/html/2607.06544#bib.bib38)\)\. With a sufficiently large corpus of social media interactions of a political group, GPT\-style models can even be fine\-tuned to inquire worldviews of the particular community\(Jiang et al\.,[2022](https://arxiv.org/html/2607.06544#bib.bib75)\)\. In addition to this, the ideological stance of LLMs reflects the deep\-rooted worldview of their creators\. They are also influenced by the geopolitical region of their creation and the language they were created in\(Buyl et al\.,[2025](https://arxiv.org/html/2607.06544#bib.bib37)\)\. With their increasing use in Information Retrieval \(IR\), it is essential to consider the origin of these models along with the worldview they reflect\.

A widely used approach for building language models for low\-resource languages involves fine\-tuning of multilingual foundation models\. Even though this approach seems to help in overcoming the resource scarcity issue, these language models internally ‘think’ in English while processing other languages\. A research work\(Wendler et al\.,[2024](https://arxiv.org/html/2607.06544#bib.bib171)\)showed that English is used as the internal pivot language in multilingual models trained on unbalanced, English\-dominated corpora\. This work demonstrated an abstract ‘concept space’ in the intermediate layers of the transformer model architecture, where a proximity of the embeddings to English tokens rather than the input language was observed\. This finding instills English as a pivot language in a semantic sense rather than a lexical one\. This kind of internal representation bias inside transformer models poses difficulty for Indic NLP by revealing the hidden English dominance\. The Anglocentric bias could incline the model to certain linguistic elements, such as lexicon and grammar\. Efforts such as Indic\-TunedLens\(Panchal et al\.,[2026](https://arxiv.org/html/2607.06544#bib.bib118)\)have proposed a framework for interpretability for Indic languages by learning shared affine transformations\.

LLMs play a key role in documenting and disseminating diverse knowledge systems\. They can reflect the embedded value systems and worldviews of different cultures\. Due to this capability, they can be used to build local dialect datasets and community\-focused language models, to preserve diverse scripts, and also for educational purposes\. The current necessity is ‘culture sensing’ where LLMs not only process or generate data, but also retain the writing style, storytelling pattern, and the innate worldview\.

### 5\.2\.Culture Sensing

AI foundation models can operate using multiple languages\. But they do not contain the lived experience of the language speakers that reflects the correlated cultural meaning\. The interplay between language and culture has long been studied to understand how the perceptions, beliefs, and values of people are encoded linguistically\(Kramsch,[2014](https://arxiv.org/html/2607.06544#bib.bib87)\)\. Integration of AI into indigenous knowledge frameworks coming from communities needs the negotiation of needs and motivations, and establishment of relevant meanings\(Lewis et al\.,[2024](https://arxiv.org/html/2607.06544#bib.bib102)\)\. It is the need of the hour to utilize the enormous capacity of AI towards understanding and preserving the cultural and linguistic diversity\. Underrepresentation of the Indic languages and the diverse cultural traditions is an understudied topic\.

Culture Sensing aims to amend the current\-day foundation models based on hermeneutic reasoning\. Culture Sensing approaches narrative diversity in AI using the abundant knowledge in indigenous communities that can be available mostly in the form of speech\. In this section, we briefly discuss our proposed approach for culture sensing along with a few future directions\.

#### 5\.2\.1\.Culture Sensing for Oral Community Knowledge

![Refer to caption](https://arxiv.org/html/2607.06544v1/images/culture_sensing.png)Figure 7\.Reference Architecture for Culture SensingOral data and storytelling are characteristic knowledge\-sharing practices in indigenous, close\-knit communities\. A thorough analysis of such oral knowledge can uncover the fundamental worldview and the value system of the community in focus\. Indigenous worldviews provide a holistic outlook and emphasize the relationship between humankind and nature as symbiotic\. On the contrary, the mainstream or conventional worldview stems from the modern industrial advancements and is reductionist, individualistic, and places humankind in a predominant position compared to nature\. A majority of the formal literature encapsulates the conventional worldview, while the native worldview is mostly present in the lived experience of the community and is context\-dependent\. The stark contrast between these two worldviews has resulted in the isolation of the indigenous knowledge in the mainstream systems, including AI applications\. The native communities are at a disadvantage due to their limited digital presence, ultimately leading to the marginalization of their pluralistic discourse\.

Bringing AI into the picture can lead to beneficial outcomes due to the trainability of the AI models\.\(Aparna et al\.,[2024](https://arxiv.org/html/2607.06544#bib.bib8)\)proposed an architecture using NLP, ASR, and Retrieval Augmented Generation \(RAG\) to address the problem of preserving and disseminating oral community knowledge\. This architecture also aims to reveal the underlying native worldviews and also understand how they deviate from the mainstream worldview\(Srivatsa et al\.,[2026](https://arxiv.org/html/2607.06544#bib.bib159)\)\. Here, an ASR pipeline is designed to convert a speech corpus to a searchable text corpus\. The speech corpus is made of audio files collected from rural communities in the state of Karnataka, India\. The audio files contain natural speech from the rural community members\. Following this, the text corpus is utilized in multiple NLP applications such as keyword search and NER\. This work also compares the community worldview with the mainstream worldview using corpora extracted from the corresponding groups\. This is done using semantic analysis of embedding neighborhoods and RAG\.

A general approach for Culture Sensing is shown in Figure[7](https://arxiv.org/html/2607.06544#S5.F7)\. This pipeline can be adapted for different use cases\. As part of this work, we have developed two applications:Graama Kannada\(Srivatsa et al\.,[2024](https://arxiv.org/html/2607.06544#bib.bib160)\), andParichaya\(Srivatsa et al\.,[2025](https://arxiv.org/html/2607.06544#bib.bib161)\)\. TheGraama Kannadaapplication supports audio search and uses an audio corpus collected from theNamma Halli Radio101010[https://blog\.janastu\.org/covid\-19\-campaign\-namma\-halli\-radio/](https://blog.janastu.org/covid-19-campaign-namma-halli-radio/)organization\. This application aims to tackle two challenges: handling noisy, dialectal, and small speech corpora and maintaining low application development cost\. Using a fuzzy search technique of n\-gram texts, this application performs keyword search efficiently in the case of the low\-resource language Kannada\. The ASR model used in this work demonstrates a comparable WER to output the audio transcripts that support the keyword search functionality\.

Parichayais an application for the management of a rural colloquial audio corpus on the topic of sandalwood cultivation\. It contains two interfaces to enable users to interact with the audio content\. The first interface enables browsing of the content using frequently occurring keywords and the corresponding context words, supporting a Keywords in Context \(KWIC\) analysis\. This helps to gather an understanding of the unique aspects of information in the speech corpus\. It also provides a surface\-level interpretation of the corpus content\. The second is a question\-answering interface that provides an answer relevant to the input question along with a summary\. The users can also listen to the audio fragments that contain the answers to the question\. Both of these applications provides access to lesser\-known corpora and enable discourse analysis to understand the crucial insights\. Unlike the mainstream knowledge sources that exhibit the conventional worldview, these applications disclose some alternate narratives and diverging worldviews\.

Table 6\.Future Directions for Culture SensingThese studies clearly showcase that the well\-established, homogeneous worldview embedded in most of the datasets that are used for training the LLMs differs substantially from the numerous unique, underrepresented native knowledge systems\. AI can be used to preserve such indigenous worldviews by representing the plural, heterogeneous discourses\. This early study demonstrates the lack of hermeneutic diversity in foundation models\. Further work in this direction can help strengthen both the cultural and linguistic representation in LLMs and the underlying narrative diversity\. A few suggestions in this regard, positioned across three verticals: data, model, and users, are listed in Table[6](https://arxiv.org/html/2607.06544#S5.T6)\.

## 6\.Conclusions

The rapid growth of the Web and AI has brought out numerous applications\. Especially in areas such as NLP, different paradigms have been proposed that have demonstrated exemplary performance\. Deep learning has further incentivized the language modeling task by introducing foundation models with state\-of\-the\-art performance\. These developments have become both boon and bane in the case of Indic languages\. On one hand, Indic NLP is becoming more efficient with time, and more LLMs for Indic languages have been coming up\. However, this rapid growth has also resulted in the homogenization of hermeneutics, linguistic biases, and the risk of loss of representation of multiple worldviews\.

In this paper, we present an overview of Natural Language Processing \(NLP\) in the context of Indic languages\. We discuss the unique characteristics of these languages and how they differ from English\. Additionally, we address the challenges that these distinctive features present when applying different NLP techniques to model Indic languages\. Finally, we provide a comprehensive overview of the historical development of Indic NLP, highlighting the evolution of NLP techniques over time\.

Ultimately, we propose Culture Sensing to enable foundation models to represent diverse and heterogeneous worldviews\. Culture Sensing aims to integrate the vast amount of native knowledge available in various forms, including speech and text, into the framework of AI\. This initiative is focused on ensuring that the pluralistic and vibrant worldviews are included\. It addresses the urgent need for inclusivity in today’s AI models\. By providing a generic research direction in this area, we hope to inspire future projects that include diverse narratives from different underrepresented regions\.

## Ethics and Privacy Statement

In developing theCulture Sensingframework, we have prioritized the preservation of linguistic and hermeneutic diversity and the mitigation of algorithmic biases that would otherwise homogenize worldviews or misrepresent the lesser\-known Indic languages\. This work recognizes that linguistic and cultural data are important components and require high levels of stewardship\. We emphasize that all data mentioned in this work are derived from publicly available, ethically sourced corpora, and this work respects the cultural nuances and intellectual authority of the represented communities\. We acknowledge the potential misrepresentation of cultural narratives associated with automatic analysis and recommend human\-in\-the\-loop validation for all downstream use cases\.

##### Generative AI Usage Acknowledgment

During the preparation of this work, the authors used Generative AI tools to assist with language refinement, clear phrasing, and image editing\. All content generated by these tools was thoroughly reviewed, edited, and validated by the authors\.

## References

- \(1\)
- Agarwal et al\.\(2025\)Dhruv Agarwal, Mor Naaman, and Aditya Vashistha\. 2025\.AI Suggestions Homogenize Writing Toward Western Styles and Diminish Cultural Nuances\. In*Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems**\(CHI ’25\)*\. Association for Computing Machinery, New York, NY, USA, Article 1117, 21 pages\.[doi:10\.1145/3706598\.3713564](https://doi.org/10.1145/3706598.3713564)
- Agarwal et al\.\(2026\)Dhruv Agarwal, Anya Shukla, Sunayana Sitaram, and Aditya Vashistha\. 2026\.Fluent but Foreign: Even Regional LLMs Lack Cultural Alignment\.arXiv:2505\.21548 \[cs\.CL\][https://arxiv\.org/abs/2505\.21548](https://arxiv.org/abs/2505.21548)
- Ahsan et al\.\(2010\)Arafat Ahsan, Prasanth Kolachina, Sudheer Kolachina, Dipti Misra, and Rajeev Sangal\. 2010\.Coupling Statistical Machine Translation with Rule\-based Transfer and Generation\. In*Proceedings of the 9th Conference of the Association for Machine Translation in the Americas: Research Papers*\. Association for Machine Translation in the Americas, Denver, Colorado, USA\.[https://aclanthology\.org/2010\.amta\-papers\.6/](https://aclanthology.org/2010.amta-papers.6/)
- AI \(2024\)Bhabha AI\. 2024\.*Gajendra: 7B Hindi\-Hinglish\-English instruction finetuned model*\.Retrieved May 13, 2026 from[https://huggingface\.co/BhabhaAI/Gajendra\-v0\.1](https://huggingface.co/BhabhaAI/Gajendra-v0.1)
- AIForAll \(2018\)AIForAll 2018\.National Strategy for Artificial Intelligence\.Accessed at[https://www\.niti\.gov\.in/sites/default/files/2023\-03/National\-Strategy\-for\-Artificial\-Intelligence\.pdf](https://www.niti.gov.in/sites/default/files/2023-03/National-Strategy-for-Artificial-Intelligence.pdf)\.\[Online; accessed 01\-May\-2026\]\.
- Ambati et al\.\(2010\)Bharat Ram Ambati, Samar Husain, Joakim Nivre, and Rajeev Sangal\. 2010\.On the role of morphosyntactic features in Hindi dependency parsing\. In*Proceedings of the NAACL HLT 2010 First Workshop on Statistical Parsing of Morphologically\-Rich Languages*\. 94–102\.
- Aparna et al\.\(2024\)M\. Aparna, Sharath Srivatsa, G\. Sai Madhavan, T\. B\. Dinesh, and Srinath Srinivasa\. 2024\.AI\-Based Assistance for Management of Oral Community Knowledge in Low\-Resource and Colloquial Kannada Language\. In*Big Data Analytics in Astronomy, Science, and Engineering*, Shelly Sachdeva and Yutaka Watanobe \(Eds\.\)\. Springer Nature Switzerland, Cham, 3–16\.
- Aravapalli et al\.\(2024\)Akhilesh Aravapalli, Mounika Marreddy, Radhika Mamidi, Manish Gupta, and Subba Reddy Oota\. 2024\.IndicSentEval: How Effectively do Multilingual Transformer Models encode Linguistic Properties for Indic Languages?*arXiv preprint arXiv:2410\.02611*\(2024\)\.
- Balachandran \(2023\)Abhinand Balachandran\. 2023\.Tamil\-Llama: A New Tamil Language Model Based on Llama 2\.arXiv:2311\.05845 \[cs\.CL\][https://arxiv\.org/abs/2311\.05845](https://arxiv.org/abs/2311.05845)
- Baruah et al\.\(2021\)Rupjyoti Baruah, Rajesh Kumar Mundotiya, and Anil Kumar Singh\. 2021\.Low resource neural machine translation: Assamese to/from other indo\-aryan \(indic\) languages\.*Transactions on Asian and Low\-Resource Language Information Processing*21, 1 \(2021\), 1–32\.
- Begum et al\.\(2008\)Rafiya Begum, Samar Husain, Arun Dhwaj, Dipti Misra Sharma, Lakshmi Bai, and Rajeev Sangal\. 2008\.Dependency Annotation Scheme for Indian Languages\. In*Proceedings of the Third International Joint Conference on Natural Language Processing: Volume\-II*\.[https://aclanthology\.org/I08\-2099/](https://aclanthology.org/I08-2099/)
- Bhagat et al\.\(2026\)Kirti Bhagat, Shaily Bhatt, Athul Velagapudi, Aditya Vashistha, Shachi Dave, and Danish Pruthi\. 2026\.TALES: A Taxonomy and Analysis of Cultural Representations in LLM\-generated Stories\. In*Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems**\(CHI ’26\)*\. Association for Computing Machinery, New York, NY, USA, Article 984, 26 pages\.[doi:10\.1145/3772318\.3790519](https://doi.org/10.1145/3772318.3790519)
- Bharati et al\.\(2003a\)Akshar Bharati, Vineet Chaitanya, Amba P\. Kulkarni, and Rajeev Sangal\. 2003a\.Language Access: An Information Based Approach\.arXiv:cs/0308019 \[cs\.CL\][https://arxiv\.org/abs/cs/0308019](https://arxiv.org/abs/cs/0308019)
- Bharati et al\.\(2003b\)Akshar Bharati, Vineet Chaitanya, Amba P\. Kulkarni, Rajeev Sangal, and G Umamaheshwara Rao\. 2003b\.Anusaaraka: Overcoming the Language Barrier in India\.arXiv:cs/0308018 \[cs\.CL\][https://arxiv\.org/abs/cs/0308018](https://arxiv.org/abs/cs/0308018)
- Bharati et al\.\(1991\)Akshar Bharati, Vineet Chaitanya, and Rajeev Sangal\. 1991\.Local word grouping and its relevance to Indian languages\.*Frontiers in Knowledge Based Computing \(KBCS90\), VP Bhatkar and KM Rege \(eds\.\), Narosa Publishing House, New Delhi*\(1991\), 277–296\.
- Bharati et al\.\(2002a\)Akshar Bharati, Vineet Chaitanya, Rajeev Sangal, and Brendan Gillon\. 2002a\.Natural Language Processing: A Paninian Perspective\.\(07 2002\)\.
- Bharati et al\.\(2009a\)Akshar Bharati, Mridul Gupta, Vineet Yadav, Karthik Gali, and Dipti Misra Sharma\. 2009a\.Simple parser for Indian languages in a dependency framework\. In*Proceedings of the Third Linguistic Annotation Workshop \(LAW III\)*\. 162–165\.
- Bharati et al\.\(2008\)Akshar Bharati, Samar Husain, Bharat Ambati, Sambhav Jain, Dipti Sharma, and Rajeev Sangal\. 2008\.Two semantic features make all the difference in parsing accuracy\.*Proc\. of ICON*8 \(2008\)\.
- Bharati et al\.\(2009b\)Akshar Bharati, Samar Husain, Dipti Misra Sharma, and Rajeev Sangal\. 2009b\.Two stage constraint based hybrid approach to free word order language dependency parsing\. In*Proceedings of the 11th International Conference on Parsing Technologies \(IWPT’09\)*\. 77–80\.
- Bharati et al\.\(2009c\)Akshar Bharati, Samar Husain, Meher Vijay, Kalyan Deepak, Dipti Misra Sharma, and Rajeev Sangal\. 2009c\.Constraint based hybrid approach to parsing indian languages\. In*Proceedings of the 23rd Pacific Asia Conference on Language, Information and Computation*\. Waseda University, 614–621\.
- Bharati and Sangal \(1990\)Akshar Bharati and Rajeev Sangal\. 1990\.A Karaka Based Approach to Parsing of Indian Languages\. In*COLING 1990 Volume 3: Papers presented to the 13th International Conference on Computational Linguistics*\.[https://aclanthology\.org/C90\-3005/](https://aclanthology.org/C90-3005/)
- Bharati and Sangal \(1993\)Akshar Bharati and Rajeev Sangal\. 1993\.Parsing free word order languages in the Paninian framework\. In*Proceedings of the 31st Annual Meeting on Association for Computational Linguistics*\(Columbus, Ohio\)*\(ACL ’93\)*\. Association for Computational Linguistics, USA, 105–111\.[doi:10\.3115/981574\.981589](https://doi.org/10.3115/981574.981589)
- Bharati et al\.\(2002c\)Akshar Bharati, Rajeev Sangal, Vineet Chaitanya, Amba Kulkarni, Dipti Misra Sharma, and KV Ramakrishnamacharyulu\. 2002c\.Anncorra: building tree\-banks in indian languages\. In*COLING\-02: The 3rd Workshop on Asian Language Resources and International Standardization*\.
- Bharati et al\.\(2002b\)Akshar Bharati, Rajeev Sangal, and T Papi Reddy\. 2002b\.A constraint based parser using integer programming\.*Proc\. of ICON*274 \(2002\)\.
- Bharati et al\.\(2003c\)Akshar Bharati, Dipti Sharma, Vineet Chaitanya, Amba Kulkarni, Rajeev Sangal, and Durgesh Rao\. 2003c\.LERIL: Collaborative Effort for Creating Lexical Resources\.*CoRR*cs\.CL/0308020 \(08 2003\)\.[doi:10\.48550/arXiv\.cs/0308020](https://doi.org/10.48550/arXiv.cs/0308020)
- Bhashadaan \(2025\)Bhashadaan 2025\.Bhashadaan: One platform, Multiple crowdsourcing initiatives\.Accessed at[https://bhashadaan\.bhashini\.co\.in/bhashadaan/en/home](https://bhashadaan.bhashini.co.in/bhashadaan/en/home)\.\[Online; accessed 20\-June\-2026\]\.
- Bhat \(2012\)Suma Bhat\. 2012\.Morpheme Segmentation for Kannada Standing on the Shoulder of Giants\. In*Proceedings of the 3rd Workshop on South and Southeast Asian Natural Language Processing, WSSANLP@COLING 2012, Mumbai, India, December 8, 2012*, Virach Sornlertlamvanich and Abbas Malik \(Eds\.\)\. The COLING 2012 Organizing Committee, 79–94\.[https://aclanthology\.org/W12\-5007/](https://aclanthology.org/W12-5007/)
- Bhattacharyya \(2010\)Pushpak Bhattacharyya\. 2010\.IndoWordNet\. In*Proceedings of the Seventh International Conference on Language Resources and Evaluation \(LREC’10\)*, Nicoletta Calzolari, Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odijk, Stelios Piperidis, Mike Rosner, and Daniel Tapias \(Eds\.\)\. European Language Resources Association \(ELRA\), Valletta, Malta\.[https://aclanthology\.org/L10\-1635/](https://aclanthology.org/L10-1635/)
- Bhattacharyya et al\.\(2019\)Pushpak Bhattacharyya, Hema Murthy, Surangika Ranathunga, and Ranjiva Munasinghe\. 2019\.Indic language computing\.*Commun\. ACM*62, 11 \(2019\), 70–75\.
- Bhingardive et al\.\(2014\)Sudha Bhingardive, Tanuja Ajotikar, Irawati Kulkarni, Malhar Kulkarni, and Pushpak Bhattacharyya\. 2014\.Semi\-Automatic Extension of Sanskrit Wordnet using Bilingual Dictionary\. In*Proceedings of the Seventh Global Wordnet Conference*, Heili Orav, Christiane Fellbaum, and Piek Vossen \(Eds\.\)\. University of Tartu Press, Tartu, Estonia, 324–329\.[https://aclanthology\.org/W14\-0145/](https://aclanthology.org/W14-0145/)
- Bhogale et al\.\(2022\)Kaushal Santosh Bhogale, Abhigyan Raman, Tahir Javed, Sumanth Doddapaneni, Anoop Kunchukuttan, Pratyush Kumar, and Mitesh M\. Khapra\. 2022\.Effectiveness of Mining Audio and Text Pairs from Public Data for Improving ASR Systems for Low\-Resource Languages\.arXiv:2208\.12666 \[cs\.CL\][https://arxiv\.org/abs/2208\.12666](https://arxiv.org/abs/2208.12666)
- Blodgett and O’Connor \(2017\)Su Lin Blodgett and Brendan O’Connor\. 2017\.Racial Disparity in Natural Language Processing: A Case Study of Social Media African\-American English\.arXiv:1707\.00061 \[cs\.CY\][https://arxiv\.org/abs/1707\.00061](https://arxiv.org/abs/1707.00061)
- Bommasani et al\.\(2022a\)Rishi Bommasani, Kathleen A\. Creel, Ananya Kumar, Dan Jurafsky, and Percy S Liang\. 2022a\.Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?\. In*Advances in Neural Information Processing Systems*, S\. Koyejo, S\. Mohamed, A\. Agarwal, D\. Belgrave, K\. Cho, and A\. Oh \(Eds\.\), Vol\. 35\. Curran Associates, Inc\., 3663–3678\.[https://proceedings\.neurips\.cc/paper\_files/paper/2022/file/17a234c91f746d9625a75cf8a8731ee2\-Paper\-Conference\.pdf](https://proceedings.neurips.cc/paper_files/paper/2022/file/17a234c91f746d9625a75cf8a8731ee2-Paper-Conference.pdf)
- Bommasani et al\.\(2022b\)Rishi Bommasani, Drew A\. Hudson, Ehsan Adeli, Russ Altman, Simran Arora, Sydney von Arx, Michael S\. Bernstein, Jeannette Bohg, Antoine Bosselut, Emma Brunskill, Erik Brynjolfsson, Shyamal Buch, Dallas Card, Rodrigo Castellon, Niladri Chatterji, Annie Chen, Kathleen Creel, Jared Quincy Davis, Dora Demszky, Chris Donahue, Moussa Doumbouya, Esin Durmus, Stefano Ermon, John Etchemendy, Kawin Ethayarajh, Li Fei\-Fei, Chelsea Finn, Trevor Gale, Lauren Gillespie, Karan Goel, Noah Goodman, Shelby Grossman, Neel Guha, Tatsunori Hashimoto, Peter Henderson, John Hewitt, Daniel E\. Ho, Jenny Hong, Kyle Hsu, Jing Huang, Thomas Icard, Saahil Jain, Dan Jurafsky, Pratyusha Kalluri, Siddharth Karamcheti, Geoff Keeling, Fereshte Khani, Omar Khattab, Pang Wei Koh, Mark Krass, Ranjay Krishna, Rohith Kuditipudi, Ananya Kumar, Faisal Ladhak, Mina Lee, Tony Lee, Jure Leskovec, Isabelle Levent, Xiang Lisa Li, Xuechen Li, Tengyu Ma, Ali Malik, Christopher D\. Manning, Suvir Mirchandani, Eric Mitchell, Zanele Munyikwa, Suraj Nair, Avanika Narayan, Deepak Narayanan, Ben Newman, Allen Nie, Juan Carlos Niebles, Hamed Nilforoshan, Julian Nyarko, Giray Ogut, Laurel Orr, Isabel Papadimitriou, Joon Sung Park, Chris Piech, Eva Portelance, Christopher Potts, Aditi Raghunathan, Rob Reich, Hongyu Ren, Frieda Rong, Yusuf Roohani, Camilo Ruiz, Jack Ryan, Christopher Ré, Dorsa Sadigh, Shiori Sagawa, Keshav Santhanam, Andy Shih, Krishnan Srinivasan, Alex Tamkin, Rohan Taori, Armin W\. Thomas, Florian Tramèr, Rose E\. Wang, William Wang, Bohan Wu, Jiajun Wu, Yuhuai Wu, Sang Michael Xie, Michihiro Yasunaga, Jiaxuan You, Matei Zaharia, Michael Zhang, Tianyi Zhang, Xikun Zhang, Yuhui Zhang, Lucia Zheng, Kaitlyn Zhou, and Percy Liang\. 2022b\.On the Opportunities and Risks of Foundation Models\.arXiv:2108\.07258 \[cs\.LG\][https://arxiv\.org/abs/2108\.07258](https://arxiv.org/abs/2108.07258)
- Brahma et al\.\(2025\)Maharaj Brahma, N J Karthika, Atul Singh, Devaraj Adiga, Smruti Bhate, Ganesh Ramakrishnan, Rohit Saluja, and Maunendra Sankar Desarkar\. 2025\.MorphTok: Morphologically Grounded Tokenization for Indian Languages\.arXiv:2504\.10335 \[cs\.CL\][https://arxiv\.org/abs/2504\.10335](https://arxiv.org/abs/2504.10335)
- Buyl et al\.\(2025\)Maarten Buyl, Alexander Rogiers, Sander Noels, Guillaume Bied, Iris Dominguez\-Catena, Edith Heiter, Iman Johary, Alexandru\-Cristian Mara, Raphaël Romero, Jefrey Lijffijt, and Tijl De Bie\. 2025\.Large Language Models Reflect the Ideology of their Creators\.arXiv:2410\.18417 \[cs\.CL\][https://arxiv\.org/abs/2410\.18417](https://arxiv.org/abs/2410.18417)
- Ceron et al\.\(2024\)Tanise Ceron, Neele Falk, Ana Barić, Dmitry Nikolaev, and Sebastian Padó\. 2024\.Beyond prompt brittleness: Evaluating the reliability and consistency of political worldviews in llms\.*Transactions of the Association for Computational Linguistics*12 \(2024\), 1378–1400\.
- Chadha et al\.\(2022\)Harveen Singh Chadha, Anirudh Gupta, Priyanshi Shah, Neeraj Chhimwal, Ankur Dhuriya, Rishabh Gaur, and Vivek Raghavan\. 2022\.Vakyansh: ASR Toolkit for Low Resource Indic languages\.arXiv:2203\.16512 \[cs\.CL\][https://arxiv\.org/abs/2203\.16512](https://arxiv.org/abs/2203.16512)
- Chaudhury et al\.\(2010\)Sriram Chaudhury, Ankitha Rao, and Dipti M Sharma\. 2010\.Anusaaraka: An expert system based machine translation system\. In*Proceedings of the 6th International Conference on Natural Language Processing and Knowledge Engineering\(NLPKE\-2010\)*\. 1–6\.[doi:10\.1109/NLPKE\.2010\.5587789](https://doi.org/10.1109/NLPKE.2010.5587789)
- Chi et al\.\(2021\)Zewen Chi, Li Dong, Furu Wei, Nan Yang, Saksham Singhal, Wenhui Wang, Xia Song, Xian\-Ling Mao, Heyan Huang, and Ming Zhou\. 2021\.InfoXLM: An Information\-Theoretic Framework for Cross\-Lingual Language Model Pre\-Training\. In*Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies*, Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani\-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, and Yichao Zhou \(Eds\.\)\. Association for Computational Linguistics, Online, 3576–3588\.[doi:10\.18653/v1/2021\.naacl\-main\.280](https://doi.org/10.18653/v1/2021.naacl-main.280)
- Choudhary and Sukhvir \(2025\)Anand Choudhary and Singh Sukhvir\. 2025\.Leveraging AI for the recreation and restoration of ancient Indian costumes and accessories\.*Tekstilec*68, 3 \(2025\), 210–226\.
- Choudhary \(2021\)Narayan Choudhary\. 2021\.LDC\-IL: The Indian repository of resources for language technology\.*Language Resources and Evaluation*55 \(01 2021\)\.[doi:10\.1007/s10579\-020\-09523\-3](https://doi.org/10.1007/s10579-020-09523-3)
- Choudhury et al\.\(2006\)Monojit Choudhury, Monjur Alam, Sudeshna Sarkar, and Anupam Basu\. 2006\.A rewrite rule based model of bangla morphophonological change\.*Proc\. of ICCPB*\(2006\), 64–71\.
- Conneau et al\.\(2019\)Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov\. 2019\.Unsupervised Cross\-lingual Representation Learning at Scale\.*CoRR*abs/1911\.02116 \(2019\)\.arXiv:1911\.02116[http://arxiv\.org/abs/1911\.02116](http://arxiv.org/abs/1911.02116)
- CoRover\.ai \(2024\)CoRover\.ai\. 2024\.*Indigenous Sovereign AI Language Models*\.Retrieved May 13, 2026 from[https://bharatgpt\.ai/](https://bharatgpt.ai/)
- Creel and Hellman \(2022\)Kathleen Creel and Deborah Hellman\. 2022\.The Algorithmic Leviathan: Arbitrariness, Fairness, and Opportunity in Algorithmic Decision\-Making Systems\.*Canadian Journal of Philosophy*52, 1 \(2022\), 26–43\.[doi:10\.1017/can\.2022\.3](https://doi.org/10.1017/can.2022.3)
- Dalal et al\.\(2006\)Aniket Dalal, Kumar Nagaraj, Uma Sawant, and Sandeep Shelke\. 2006\.Hindi Part\-of\-Speech Tagging and Chunking : A Maximum Entropy Approach\.\(01 2006\)\.
- Dalal et al\.\(2007\)Aniket Dalal, Kumar Nagaraj, U Swant, Sandeep Shelke, and Pushpak Bhattacharyya\. 2007\.Building feature rich pos tagger for morphologically rich languages: Experience in Hindi\.*ICON*\(2007\)\.
- Dandapat et al\.\(2004\)Sandipan Dandapat, Sudeshna Sarkar, and Basu Anupam\. 2004\.A Hybrid Model for Part\-of\-Speech Tagging and its Application to Bengali\. 169–172\.
- Das et al\.\(2025\)Sudhansu Bala Das, Samujjal Choudhury, Dr Tapas Kumar Mishra, and Dr Bidyut Kr Patra\. 2025\.Investigating the Effect of Backtranslation for Indic Languages\. In*Proceedings of the First Workshop on Natural Language Processing for Indo\-Aryan and Dravidian Languages*, Ruvan Weerasinghe, Isuri Anuradha, and Deshan Sumanathilaka \(Eds\.\)\. Association for Computational Linguistics, Abu Dhabi, 152–165\.[https://aclanthology\.org/2025\.indonlp\-1\.18/](https://aclanthology.org/2025.indonlp-1.18/)
- Dasari et al\.\(2023\)Priyanka Dasari, Abhijith Chelpuri, Nagaraju Vuppala, Mounika Marreddy, Parameshwari Krishnamurthy, and Radhika Mamidi\. 2023\.Transformer\-based Context Aware Morphological Analyzer for Telugu\. In*Proceedings of the Third Workshop on Speech and Language Technologies for Dravidian Languages*\. 25–32\.
- Dash and Chaudhuri \(2001\)NILADRI SEKHAR Dash and BIDYUT BARAN Chaudhuri\. 2001\.Why do we need to develop corpora in Indian languages\. In*the International Working Conference on Sharing Capability in Localisation and Human Language Technologies SCALLA\-2001\. Bangalore*\.
- Dave et al\.\(2001\)Shachi Dave, Jignashu Parikh, and Pushpak Bhattacharyya\. 2001\.Interlingua\-based English–Hindi machine translation and language divergence\.*Machine Translation*16 \(2001\), 251–304\.
- Devlin et al\.\(2019\)Jacob Devlin, Ming\-Wei Chang, Kenton Lee, and Kristina Toutanova\. 2019\.BERT: Pre\-training of Deep Bidirectional Transformers for Language Understanding\.arXiv:1810\.04805 \[cs\.CL\][https://arxiv\.org/abs/1810\.04805](https://arxiv.org/abs/1810.04805)
- Diwakar et al\.\(2010\)Sapan Diwakar, Pulkit Goyal, and Rohit Gupta\. 2010\.Transliteration among indian languages using wx notation\. In*Proceedings of the conference on natural language processing 2010*\. Saarland University Press, 147–150\.
- DocBodh \(2025\)DocBodh 2025\.DocBodh: AI\-native document understanding for India\.Accessed at[https://bharatgen\.com/products/docbodh/](https://bharatgen.com/products/docbodh/)\.\[Online; accessed 01\-March\-2026\]\.
- Doddapaneni et al\.\(2023\)Sumanth Doddapaneni, Rahul Aralikatte, Gowtham Ramesh, Shreya Goyal, Mitesh M Khapra, Anoop Kunchukuttan, and Pratyush Kumar\. 2023\.Towards leaving no indic language behind: Building monolingual corpora, benchmark and models for indic languages\. In*Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics \(Volume 1: Long Papers\)*\. 12402–12426\.
- Elfeky et al\.\(2018\)Mohamed G\. Elfeky, Pedro Moreno, and Victor Soto\. 2018\.Multi\-Dialectical Languages Effect on Speech Recognition: Too Much Choice Can Hurt\.*Procedia Computer Science*128 \(2018\), 1–8\.[doi:10\.1016/j\.procs\.2018\.03\.001](https://doi.org/10.1016/j.procs.2018.03.001)1st International Conference on Natural Language and Speech Processing\.
- Gala et al\.\(2023\)Jay Gala, Pranjal A\. Chitale, Raghavan AK, Varun Gumma, Sumanth Doddapaneni, Aswanth Kumar, Janki Nawale, Anupama Sujatha, Ratish Puduppully, Vivek Raghavan, Pratyush Kumar, Mitesh M\. Khapra, Raj Dabre, and Anoop Kunchukuttan\. 2023\.IndicTrans2: Towards High\-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages\.arXiv:2305\.16307 \[cs\.CL\][https://arxiv\.org/abs/2305\.16307](https://arxiv.org/abs/2305.16307)
- Gala et al\.\(2024\)Jay Gala, Thanmay Jayakumar, Jaavid Aktar Husain, Aswanth Kumar M, Mohammed Safi Ur Rahman Khan, Diptesh Kanojia, Ratish Puduppully, Mitesh M\. Khapra, Raj Dabre, Rudra Murthy, and Anoop Kunchukuttan\. 2024\.Airavata: Introducing Hindi Instruction\-tuned LLM\.arXiv:2401\.15006 \[cs\.CL\][https://arxiv\.org/abs/2401\.15006](https://arxiv.org/abs/2401.15006)
- Gandhe et al\.\(2011\)Ankur Gandhe, Rashmi Gangadharaiah, Karthik Visweswariah, and Ananthakrishnan Ramanathan\. 2011\.Handling verb phrase morphology in highly inflected Indian languages for Machine Translation\. In*Proceedings of 5th international joint conference on natural language processing*\. 111–119\.
- Gorla et al\.\(2008\)Jagadeesh Gorla, Anil Kumar Singh, Rajeev Sangal, Karthik Gali, Samar Husain, and Sriram Venkatapathy\. 2008\.A Graph Based Method for Building Multilingual Weakly Supervised Dependency Parsers\. In*Advances in Natural Language Processing*, Bengt Nordström and Aarne Ranta \(Eds\.\)\. Springer Berlin Heidelberg, Berlin, Heidelberg, 148–159\.
- Goyal et al\.\(2020\)Vikrant Goyal, Sourav Kumar, and Dipti Misra Sharma\. 2020\.Efficient neural machine translation for low\-resource languages via exploiting related languages\. In*Proceedings of the 58th annual meeting of the association for computational linguistics: student research workshop*\. 162–168\.
- Gupta et al\.\(2008\)Mridul Gupta, Vineet Yadav, Samar Husain, and Dipti M Sharma\. 2008\.A Rule Based Approach for Automatic Annotation of a Hindi Tree\-bank\. In*Proc\. Of the 6th International Conference on Natural Language Processing \(ICON\-08\), CDAC Pune, India*\.
- Hariharan and Mortensen \(2025\)Ananth Hariharan and David Mortensen\. 2025\.Transformer\-Enabled Diachronic Analysis of Vedic Sanskrit: Neural Methods for Quantifying Types of Language Change\.arXiv:2512\.05364 \[cs\.CL\][https://arxiv\.org/abs/2512\.05364](https://arxiv.org/abs/2512.05364)
- Hartmann et al\.\(2023\)Jochen Hartmann, Jasper Schwenzow, and Maximilian Witte\. 2023\.The political ideology of conversational AI: Converging evidence on ChatGPT’s pro\-environmental, left\-libertarian orientation\.arXiv:2301\.01768 \[cs\.CL\][https://arxiv\.org/abs/2301\.01768](https://arxiv.org/abs/2301.01768)
- Husain et al\.\(2009\)Samar Husain, Phani Gadde, Bharat Ambati, Dipti Misra Sharma, and Rajeev Sangal\. 2009\.A Modular Cascaded Approach to Complete Parsing\. In*2009 International Conference on Asian Language Processing*\. 141–146\.[doi:10\.1109/IALP\.2009\.37](https://doi.org/10.1109/IALP.2009.37)
- Indian Economy News \(2025\)Indian Economy News 2025\.India’s internet users to exceed 900 million in 2025, driven by Indic languages\.[https://www\.ibef\.org/news/india\-s\-internet\-users\-to\-exceed\-900\-million\-in\-2025\-driven\-by\-indic\-languages](https://www.ibef.org/news/india-s-internet-users-to-exceed-900-million-in-2025-driven-by-indic-languages)\.\[Online; accessed 20\-May\-2026\]\.
- Indian Script Code for Information Interchange \(2009\)Indian Script Code for Information Interchange 2009\.Character Encoding Standard For Indian Languages\.https://egovstandards\.gov\.in/sites/default/files/2021\-07/Character%20Encoding\-%20Standard%20Ver1\.0\.pdf\.
- ISFOC Standard for Fonts \(\[n\. d\.\]\)ISFOC Standard for Fonts \[n\. d\.\]\.ISFOC Standard for Fonts\.https://cdac\.in/index\.aspx?id=mlc\_gist\_isfoc\.
- Javed et al\.\(2022\)Tahir Javed, Kaushal Santosh Bhogale, Abhigyan Raman, Anoop Kunchukuttan, Pratyush Kumar, and Mitesh M\. Khapra\. 2022\.IndicSUPERB: A Speech Processing Universal Performance Benchmark for Indian languages\.arXiv:2208\.11761 \[cs\.CL\][https://arxiv\.org/abs/2208\.11761](https://arxiv.org/abs/2208.11761)
- Javed et al\.\(2021\)Tahir Javed, Sumanth Doddapaneni, Abhigyan Raman, Kaushal Santosh Bhogale, Gowtham Ramesh, Anoop Kunchukuttan, Pratyush Kumar, and Mitesh M\. Khapra\. 2021\.Towards Building ASR Systems for the Next Billion Users\.arXiv:2111\.03945 \[cs\.CL\][https://arxiv\.org/abs/2111\.03945](https://arxiv.org/abs/2111.03945)
- Javed et al\.\(2024\)Tahir Javed, Janki Nawale, Eldho George, Sakshi Joshi, Kaushal Bhogale, Deovrat Mehendale, Ishvinder Sethi, Aparna Ananthanarayanan, Hafsah Faquih, Pratiti Palit, Sneha Ravishankar, Saranya Sukumaran, Tripura Panchagnula, Sunjay Murali, Kunal Gandhi, Ambujavalli R, Manickam M, C Vaijayanthi, Krishnan Karunganni, Pratyush Kumar, and Mitesh Khapra\. 2024\.IndicVoices: Towards building an Inclusive Multilingual Speech Dataset for Indian Languages\. In*Findings of the Association for Computational Linguistics: ACL 2024*, Lun\-Wei Ku, Andre Martins, and Vivek Srikumar \(Eds\.\)\. Association for Computational Linguistics, Bangkok, Thailand, 10740–10782\.[doi:10\.18653/v1/2024\.findings\-acl\.639](https://doi.org/10.18653/v1/2024.findings-acl.639)
- Jiang et al\.\(2022\)Hang Jiang, Doug Beeferman, Brandon Roy, and Deb Roy\. 2022\.CommunityLM: Probing Partisan Worldviews from Language Models\.arXiv:2209\.07065 \[cs\.SI\][https://arxiv\.org/abs/2209\.07065](https://arxiv.org/abs/2209.07065)
- Joshi et al\.\(2018\)Akshat Joshi, Kinal Mehta, Neha Gupta, and Varun Kannadi Valloli\. 2018\.Indian language transliteration using deep learning\. In*2018 IEEE Recent Advances in Intelligent Computational Systems \(RAICS\)*\. IEEE, 103–107\.
- Kakwani et al\.\(2020\)Divyanshu Kakwani, Anoop Kunchukuttan, Satish Golla, Gokul N\.C\., Avik Bhattacharyya, Mitesh M\. Khapra, and Pratyush Kumar\. 2020\.IndicNLPSuite: Monolingual Corpora, Evaluation Benchmarks and Pre\-trained Multilingual Language Models for Indian Languages\. In*Findings of the Association for Computational Linguistics: EMNLP 2020*, Trevor Cohn, Yulan He, and Yang Liu \(Eds\.\)\. Association for Computational Linguistics, Online, 4948–4961\.[doi:10\.18653/v1/2020\.findings\-emnlp\.445](https://doi.org/10.18653/v1/2020.findings-emnlp.445)
- Kallappa et al\.\(2025\)Aditya Kallappa, Palash Kamble, Abhinav Ravi, Akshat Patidar, Vinayak Dhruv, Deepak Kumar, Raghav Awasthi, Arveti Manjunath, Himanshu Gupta, Shubham Agarwal, Kumar Ashish, Gautam Bhargava, and Chandra Khatri\. 2025\.Krutrim LLM: Multilingual Foundational Model for over a Billion People\.arXiv:2502\.09642 \[cs\.CL\][https://arxiv\.org/abs/2502\.09642](https://arxiv.org/abs/2502.09642)
- Kalyanakrishnan et al\.\(2018\)Shivaram Kalyanakrishnan, Rahul Alex Panicker, Sarayu Natarajan, and Shreya Rao\. 2018\.Opportunities and Challenges for Artificial Intelligence in India\. In*Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society*\(New Orleans, LA, USA\)*\(AIES ’18\)*\. Association for Computing Machinery, New York, NY, USA, 164–170\.[doi:10\.1145/3278721\.3278738](https://doi.org/10.1145/3278721.3278738)
- Kanuparthi et al\.\(2012\)Nikhil Kanuparthi, Abhilash Inumella, and Dipti Misra Sharma\. 2012\.Hindi derivational morphological analyzer\. In*Proceedings of the Twelfth Meeting of the Special Interest Group on Computational Morphology and Phonology*\(Montreal, Canada\)*\(SIGMORPHON ’12\)*\. Association for Computational Linguistics, USA, 10–16\.
- Karthika et al\.\(2025\)NJ Karthika, Maharaj Brahma, Rohit Saluja, Ganesh Ramakrishnan, and Maunendra Sankar Desarkar\. 2025\.Multilingual Tokenization through the Lens of Indian Languages: Challenges and Insights\.*arXiv preprint arXiv:2506\.17789*\(2025\)\.
- Karthika et al\.\(2026\)N J Karthika, Keerthana Suryanarayanan, Jahanvi Purohit, Ganesh Ramakrishnan, Jitin Singla, and Anil Kumar Gourishetty\. 2026\.Samasāmayik: A Parallel Dataset for Hindi\-Sanskrit Machine Translation\.arXiv:2603\.24307 \[cs\.CL\][https://arxiv\.org/abs/2603\.24307](https://arxiv.org/abs/2603.24307)
- Khanuja et al\.\(2021\)Simran Khanuja, Diksha Bansal, Sarvesh Mehtani, Savya Khosla, Atreyee Dey, Balaji Gopalan, Dilip Kumar Margam, Pooja Aggarwal, Rajiv Teja Nagipogu, Shachi Dave, Shruti Gupta, Subhash Chandra Bose Gali, Vishnu Subramanian, and Partha Pratim Talukdar\. 2021\.MuRIL: Multilingual Representations for Indian Languages\.*ArXiv*abs/2103\.10730 \(2021\)\.[https://api\.semanticscholar\.org/CorpusID:232290691](https://api.semanticscholar.org/CorpusID:232290691)
- Khemchandani et al\.\(2021\)Yash Khemchandani, Sarvesh Mehtani, Vaidehi Patil, Abhijeet Awasthi, Partha Talukdar, and Sunita Sarawagi\. 2021\.Exploiting language relatedness for low web\-resource language model adaptation: An Indic languages study\. In*Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing \(Volume 1: Long Papers\)*\. 1312–1323\.
- Khubchandani \(1985\)Lachman M\. Khubchandani\. 1985\.Diglossia Revisited\.*Oceanic Linguistics Special Publications*20 \(1985\), 199–211\.[http://www\.jstor\.org/stable/20006723](http://www.jstor.org/stable/20006723)
- Koenecke et al\.\(2020\)Allison Koenecke, Andrew Nam, Emily Lake, Joe Nudell, Minnie Quartey, Zion Mengesha, Connor Toups, John Rickford, Dan Jurafsky, and Sharad Goel\. 2020\.Racial disparities in automated speech recognition\.*Proceedings of the National Academy of Sciences*117 \(03 2020\), 201915768\.[doi:10\.1073/pnas\.1915768117](https://doi.org/10.1073/pnas.1915768117)
- Kramsch \(2014\)Claire Kramsch\. 2014\.Language and culture\.*AILA review*27, 1 \(2014\), 30–55\.
- Krishna et al\.\(2025\)D\. Manoj Krishna, Vadini Gupta, Kiran Kumari, and Kumari Nidhi\. 2025\.Impact of AI\- Powered Translation Tools: Upholding Indian Linguistic Diversity\.*Journal of Digital Sociohumanities*\(2025\)\.[https://api\.semanticscholar\.org/CorpusID:279233826](https://api.semanticscholar.org/CorpusID:279233826)
- Kudo and Richardson \(2018\)Taku Kudo and John Richardson\. 2018\.SentencePiece: A simple and language independent subword tokenizer and detokenizer for neural text processing\.*arXiv preprint arXiv:1808\.06226*\(2018\)\.
- Kulkarni et al\.\(2012\)Amba Kulkarni, Soma Paul, Malhar Kulkarni, Anil Kumar Nelakanti, and Nitesh Surtani\. 2012\.Semantic processing of compounds in indian languages\. In*Proceedings of COLING 2012*\. 1489–1502\.
- Kulkarni and Bhattacharyya \(2009\)Malhar Kulkarni and Pushpak Bhattacharyya\. 2009\.Verbal Roots in the Sanskrit Wordnet\. In*Sanskrit Computational Linguistics*, Gérard Huet, Amba Kulkarni, and Peter Scharf \(Eds\.\)\. Springer Berlin Heidelberg, Berlin, Heidelberg, 328–338\.
- Kulkarni et al\.\(2010\)Malhar Kulkarni, Chaitali Dangarikar, Irawati Kulkarni, Abhishek Nanda, and Pushpak Bhattacharyya\. 2010\.Introducing sanskrit wordnet\. In*Proceedings on the 5th global wordnet conference \(GWC 2010\), Narosa, Mumbai*\. 287–294\.
- Kulkarni and Srinivasa \(2013\)Sumant Kulkarni and Srinath Srinivasa\. 2013\.TrieIR: Indexing and Retrieval Engine for Kannada Unicode Text\. In*Digital Libraries: Social Media and Community Networks*, Shalini R\. Urs, Jin\-Cheon Na, and George Buchanan \(Eds\.\)\. Springer International Publishing, Cham, 21–24\.[https://doi\.org/10\.1007/978\-3\-319\-03599\-4\_3](https://doi.org/10.1007/978-3-319-03599-4_3)\.
- Kumar et al\.\(2010\)Anil Kumar, Vipul Mittal, and Amba Kulkarni\. 2010\.Sanskrit Compound Processor\. In*Sanskrit Computational Linguistics*, Girish Nath Jha \(Ed\.\)\. Springer Berlin Heidelberg, Berlin, Heidelberg, 57–69\.
- Kumar et al\.\(2024a\)Sanjeev Kumar, Preethi Jyothi, and Pushpak Bhattacharyya\. 2024a\.Part\-of\-speech Tagging for Extremely Low\-resource Indian Languages\. In*Findings of the Association for Computational Linguistics: ACL 2024*, Lun\-Wei Ku, Andre Martins, and Vivek Srikumar \(Eds\.\)\. Association for Computational Linguistics, Bangkok, Thailand, 14422–14431\.[doi:10\.18653/v1/2024\.findings\-acl\.857](https://doi.org/10.18653/v1/2024.findings-acl.857)
- Kumar et al\.\(2024b\)Sanjeev Kumar, Preethi Jyothi, and Pushpak Bhattacharyya\. 2024b\.Part\-of\-speech tagging for extremely low\-resource Indian languages\. In*Findings of the Association for Computational Linguistics: ACL 2024*\. 14422–14431\.
- Kumar Navneet et al\.\(2026\)Satyam Kumar Navneet, Joydeep Chandra, and Yong Zhang\. 2026\.When AI Writes, Whose Voice Remains? Quantifying Cultural Marker Erasure Across World English Varieties in Large Language Models\. In*Proceedings of the Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems**\(CHI EA ’26\)*\. ACM, 1–7\.[doi:10\.1145/3772363\.3799085](https://doi.org/10.1145/3772363.3799085)
- Kunchukuttan and Bhattacharyya \(2012\)Anoop Kunchukuttan and Pushpak Bhattacharyya\. 2012\.Partially modelling word reordering as a sequence labelling problem\. In*Proceedings of the Workshop on Reordering for Statistical Machine Translation*\. 47–54\.
- Kunchukuttan et al\.\(2014\)Anoop Kunchukuttan, Abhijit Mishra, Rajen Chatterjee, Ritesh Shah, and Pushpak Bhattacharyya\. 2014\.Shata\-Anuvadak: Tackling Multiway Translation of Indian Languages\. In*Proceedings of the Ninth International Conference on Language Resources and Evaluation \(LREC‘14\)*, Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Hrafn Loftsson, Bente Maegaard, Joseph Mariani, Asuncion Moreno, Jan Odijk, and Stelios Piperidis \(Eds\.\)\. European Language Resources Association \(ELRA\), Reykjavik, Iceland, 1781–1787\.[https://aclanthology\.org/L14\-1355/](https://aclanthology.org/L14-1355/)
- Kunchukuttan et al\.\(2015\)Anoop Kunchukuttan, Ratish Puduppully, and Pushpak Bhattacharyya\. 2015\.Brahmi\-Net: A transliteration and script conversion system for languages of the Indian subcontinent\. In*Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations*, Matt Gerber, Catherine Havasi, and Finley Lacatusu \(Eds\.\)\. Association for Computational Linguistics, Denver, Colorado, 81–85\.[doi:10\.3115/v1/N15\-3017](https://doi.org/10.3115/v1/N15-3017)
- Lab \(2024\)Telugu LLM Lab\. 2024\.*Navarasa: Collection of Gemma finetuned 7B/ 2B Indic Navarasa models*\.Retrieved May 13, 2026 from[https://huggingface\.co/collections/Telugu\-LLM\-Labs/navarasa](https://huggingface.co/collections/Telugu-LLM-Labs/navarasa)
- Lewis et al\.\(2024\)Jason Lewis, Hēmi Whaanga, and Ceyda Yolgörmez\. 2024\.Abundant intelligences: placing AI within Indigenous knowledge frameworks\.*AI & SOCIETY*40 \(10 2024\), 2141–2157\.[doi:10\.1007/s00146\-024\-02099\-4](https://doi.org/10.1007/s00146-024-02099-4)
- M and Srinivasa \(2023\)Aparna M and Srinath Srinivasa\. 2023\.Active learning for Named Entity Recognition in Kannada\.*TechRxiv*2023, 1127 \(2023\)\.arXiv:https://www\.techrxiv\.org/doi/pdf/10\.36227/techrxiv\.24580582\.v1[doi:10\.36227/techrxiv\.24580582\.v1](https://doi.org/10.36227/techrxiv.24580582.v1)
- Maheshwari \(\[n\. d\.\]\)Deepak Maheshwari\. \[n\. d\.\]\.AI’s Global South Pivot: Equity, Ethics and Ecology\.\(\[n\. d\.\]\)\.
- Majumder and Mitra \(2002\)Prasenjit Majumder and Mandar Mitra\. 2002\.N\-gram: a language independent approach to IR and NLP\.[https://api\.semanticscholar\.org/CorpusID:6496350](https://api.semanticscholar.org/CorpusID:6496350)
- Majumder et al\.\(2007\)Prasenjit Majumder, Mandar Mitra, Swapan K Parui, Gobinda Kole, Pabitra Mitra, and Kalyankumar Datta\. 2007\.YASS: Yet another suffix stripper\.*ACM transactions on information systems \(TOIS\)*25, 4 \(2007\), 18–es\.
- Malladi and Mannem \(2013\)Deepak Kumar Malladi and Prashanth Mannem\. 2013\.Statistical morphological analyzer for hindi\. In*Proceedings of the Sixth International Joint Conference on Natural Language Processing*\. 1007–1011\.
- Manoj et al\.\(2025\)Guduru Manoj, Neel Prabhanjan Rachamalla, Ashish Kulkarni, Gautam Rajeev, Jay Piplodiya, Arul Menezes, Shaharukh Khan, Souvik Rana, Manya Sah, Chandra Khatri, and Shubham Agarwal\. 2025\.BhashaKritika: Building Synthetic Pretraining Data at Scale for Indic Languages\.arXiv:2511\.10338 \[cs\.CL\][https://arxiv\.org/abs/2511\.10338](https://arxiv.org/abs/2511.10338)
- Marco et al\.\(2024\)Guillermo Marco, Julio Gonzalo, M\.Teresa Mateo\-Girona, and Ramón Del Castillo Santos\. 2024\.Pron vs Prompt: Can Large Language Models already Challenge a World\-Class Fiction Author at Creative Text Writing?\. In*Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing*, Yaser Al\-Onaizan, Mohit Bansal, and Yun\-Nung Chen \(Eds\.\)\. Association for Computational Linguistics, Miami, Florida, USA, 19654–19670\.[doi:10\.18653/v1/2024\.emnlp\-main\.1096](https://doi.org/10.18653/v1/2024.emnlp-main.1096)
- Marimuthu and Devi \(2014\)K Marimuthu and Sobha Lalitha Devi\. 2014\.Automatic conversion of dialectal Tamil text to standard written Tamil text using FSTs\. In*Proceedings of the 2014 Joint Meeting of SIGMORPHON and SIGFSM*\. 37–45\.
- Mayura \(2025\)Mayura 2025\.Making complex information accessible with Mayura\.Accessed at[https://www\.sarvam\.ai/blogs/blog\-mayura](https://www.sarvam.ai/blogs/blog-mayura)\.\[Online; accessed 01\-March\-2026\]\.
- McEnery et al\.\(2000\)Anthony McEnery, Paul Baker, Rob Gaizauskas, and Hamish Cunningham\. 2000\.EMILLE: building a corpus of South Asian languages\. In*Proceedings of the International Conference on Machine Translation and Multilingual Applications in the new Millennium: MT 2000*\. University of Exeter, UK\.[https://aclanthology\.org/2000\.bcs\-1\.11/](https://aclanthology.org/2000.bcs-1.11/)
- Mishra and Bali \(2010\)Diwakar Mishra and Kalika Bali\. 2010\.Hindi dialects phonological transfer rules for verb rootC​e​l​eC\\reflectbox\{e\}l\\reflectbox\{e\}\. In*13th oriental COCOSDA\-2010 conference in coordination with International Committee for the Co\-ordination and Standardization of Speech Databases and Assessment Techniques held at Kathmandu\. Nepal*\. 24–25\.
- Motoki et al\.\(2023\)Fabio Motoki, Valdemar Pinho Neto, and Victor Rangel\. 2023\.More Human than Human: Measuring ChatGPT Political Bias\.*SSRN Electronic Journal*\(01 2023\)\.[doi:10\.2139/ssrn\.4372349](https://doi.org/10.2139/ssrn.4372349)
- Narang et al\.\(2013\)Ashish Narang, RK Sharma, and Parteek Kumar\. 2013\.Development of Punjabi WordNet\.*CSI transactions on ICT*1, 4 \(2013\), 349–354\.
- Neupane \(2024\)Ramnath Neupane\. 2024\.Morphological Processes in English and Sanskrit: A Cross\-Linguistic Study\.*Vox Batauli*9, 01 \(2024\), 72–79\.
- Pakray et al\.\(2025\)Partha Pakray, Reddi Krishna, Santanu Pal, Advaitha Vetagiri, Sandeep Dash, Arnab Kumar Maji, Saralin A Lyngdoh, Lenin Laitonjam, Anupam Jamatia, Koj Sambyo, et al\.2025\.Findings of WMT 2025 shared task on low\-resource indic languages translation\. In*Proceedings of the Tenth Conference on Machine Translation*\. 532–553\.
- Panchal et al\.\(2026\)Mihir Panchal, Deeksha Varshney, Mamta, and Asif Ekbal\. 2026\.Indic\-TunedLens: Interpreting Multilingual Models in Indian Languages\.[doi:10\.48550/arXiv\.2602\.15038](https://doi.org/10.48550/arXiv.2602.15038)
- Pandian and Geetha \(2008\)S\. Pandian and T\.V Geetha\. 2008\.Morpheme based Language Model for Tamil Part\-of\-Speech Tagging\.*Polibits*38 \(12 2008\), 19–25\.[doi:10\.17562/PB\-38\-2](https://doi.org/10.17562/PB-38-2)
- Param \(2025\)Param 2025\.Powering India’s AI with Contextual Understanding\.Accessed at[https://bharatgen\.com/products/bharat\-gen\-text\-model/](https://bharatgen.com/products/bharat-gen-text-model/)\.\[Online; accessed 01\-March\-2026\]\.
- Patel et al\.\(2017\)Raj Patel, Prakash Pimpale, and Sasikumar Mukundan\. 2017\.MTIL17: English to Indian Langauge Statistical Machine Translation\.\(08 2017\)\.[doi:10\.48550/arXiv\.1708\.07950](https://doi.org/10.48550/arXiv.1708.07950)
- Pawar et al\.\(2023\)Siddhesh Pawar, Pushpak Bhattacharyya, and Partha Talukdar\. 2023\.Evaluating Cross Lingual Transfer for Morphological Analysis: a Case Study of Indian Languages\. In*Proceedings of the 20th SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology*, Garrett Nicolai, Eleanor Chodroff, Frederic Mailhot, and Çağrı Çöltekin \(Eds\.\)\. Association for Computational Linguistics, Toronto, Canada, 14–26\.[doi:10\.18653/v1/2023\.sigmorphon\-1\.3](https://doi.org/10.18653/v1/2023.sigmorphon-1.3)
- Philip et al\.\(2021\)Jerin Philip, Shashank Siripragada, Vinay P Namboodiri, and CV Jawahar\. 2021\.Revisiting low resource status of indian languages in machine translation\. In*Proceedings of the 3rd ACM India Joint International Conference on Data Science & Management of Data \(8th ACM IKDD CODS & 26th COMAD\)*\. 178–187\.
- Pulikodan et al\.\(2026\)Sujith Pulikodan, Abhayjeet Singh, Agneedh Basu, Nihar Desai, Pavan Kumar J, Pranav D Bhat, Raghu Dharmaraju, Ritika Gupta, Sathvik Udupa, Saurabh Kumar, Sumit Sharma, Visruth Sanka, Dinesh Tewari, Harsh Dhand, Amrita Kamat, Sukhwinder Singh, Shikhar Vashishth, Partha Talukdar, Raj Acharya, and Prasanta Kumar Ghosh\. 2026\.VAANI: Capturing the language landscape for an inclusive digital India\.arXiv:2603\.28714 \[eess\.AS\][https://arxiv\.org/abs/2603\.28714](https://arxiv.org/abs/2603.28714)
- Radford et al\.\(2022\)Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever\. 2022\.Robust Speech Recognition via Large\-Scale Weak Supervision\.arXiv:2212\.04356 \[eess\.AS\][https://arxiv\.org/abs/2212\.04356](https://arxiv.org/abs/2212.04356)
- Rajendran et al\.\(2002\)Sankaravelayuthan Rajendran, Selvaraj Arulmozi, B Kumara Shanmugam, S Baskaran, and S Thiagarajan\. 2002\.Tamil wordnet\. In*Proceedings of the first international global WordNet conference\. Mysore*, Vol\. 152\. 271–274\.
- Ramanathan et al\.\(2011\)Ananthakrishnan Ramanathan, Pushpak Bhattacharyya, Karthik Visweswariah, Kushal Ladha, and Ankur Gandhe\. 2011\.Clause\-Based Reordering Constraints to Improve Statistical Machine Translation\. In*Proceedings of 5th International Joint Conference on Natural Language Processing*, Haifeng Wang and David Yarowsky \(Eds\.\)\. Asian Federation of Natural Language Processing, Chiang Mai, Thailand, 1351–1355\.[https://aclanthology\.org/I11\-1152/](https://aclanthology.org/I11-1152/)
- Ramanathan et al\.\(2009\)Ananthakrishnan Ramanathan, Hansraj Choudhary, Avishek Ghosh, and Pushpak Bhattacharyya\. 2009\.Case markers and Morphology: Addressing the crux of the fluency problem in English\-Hindi SMT\. In*Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP*, Keh\-Yih Su, Jian Su, Janyce Wiebe, and Haizhou Li \(Eds\.\)\. Association for Computational Linguistics, Suntec, Singapore, 800–808\.[https://aclanthology\.org/P09\-1090/](https://aclanthology.org/P09-1090/)
- Ramanathan et al\.\(2008\)Ananthakrishnan Ramanathan, Jayprasad Hegde, Ritesh M\. Shah, Pushpak Bhattacharyya, and Sasikumar M\. 2008\.Simple Syntactic and Morphological Processing Can Help English\-Hindi Statistical Machine Translation\. In*Proceedings of the Third International Joint Conference on Natural Language Processing: Volume\-I*\.[https://aclanthology\.org/I08\-1067/](https://aclanthology.org/I08-1067/)
- Ramanathan and Rao \(2003\)Ananthakrishnan Ramanathan and Durgesh Rao\. 2003\.A Lightweight Stemmer for Hindi\.[https://api\.semanticscholar\.org/CorpusID:46993455](https://api.semanticscholar.org/CorpusID:46993455)
- Ramasamy and Žabokrtskỳ \(2011\)Loganathan Ramasamy and Zdeněk Žabokrtskỳ\. 2011\.Tamil dependency parsing: results using rule based and corpus based approaches\. In*International Conference on Intelligent Text Processing and Computational Linguistics*\. Springer, 82–95\.
- Rao et al\.\(1998\)Durgesh Rao, Pushpak Bhattacharya, and Radhika Mamidi\. 1998\.Natural language generation for English to Hindi human\-aided machine translation\.*VIVEK\-BOMBAY\-*11 \(1998\), 32–39\.
- Rao et al\.\(2000\)Durgesh Rao, Kavitha Mohanraj, Jayprasad Hegde, Vivek Mehta, and Parag Mahadane\. 2000\.A practical framework for syntactic transfer of compound\-complex sentences for English\-Hindi machine translation\. In*Proceedings of KBCS*, Vol\. 2000\. Citeseer\.
- Reddy et al\.\(2009\)Siva Reddy, Abhilash Inumella, Rajeev Sangal, and Soma Paul\. 2009\.All Words Unsupervised Semantic Category Labeling for Hindi\. In*Proceedings of the International Conference RANLP\-2009*, Galia Angelova and Ruslan Mitkov \(Eds\.\)\. Association for Computational Linguistics, Borovets, Bulgaria, 365–369\.[https://aclanthology\.org/R09\-1066/](https://aclanthology.org/R09-1066/)
- Saaras V3 \(2026\)Saaras V3 2026\.Introducing Saaras V3\. Built for the Way India Speaks\.Accessed at[https://www\.sarvam\.ai/blogs/asr](https://www.sarvam.ai/blogs/asr)\.\[Online; accessed 01\-June\-2026\]\.
- Sahoo and Vidyasagar \(2003\)Kalyanamalini Sahoo and V Eshwarchandra Vidyasagar\. 2003\.Kannada WordNet\-A lexical database\. In*TENCON 2003\. Conference on Convergent Technologies for Asia\-Pacific Region*, Vol\. 4\. IEEE, 1352–1356\.
- Sandhan et al\.\(2022\)Jivnesh Sandhan, Rathin Singha, Narein Rao, Suvendu Samanta, Laxmidhar Behera, and Pawan Goyal\. 2022\.TransLIST: A Transformer\-Based Linguistically Informed Sanskrit Tokenizer\.arXiv:2210\.11753 \[cs\.CL\][https://arxiv\.org/abs/2210\.11753](https://arxiv.org/abs/2210.11753)
- Sankaran et al\.\(2008\)Baskaran Sankaran, Kalika Bali, Tanmoy Bhattacharya, Pushpak Bhattacharyya, Girish Nath Jha, S Rajendran, K Saravanan, et al\.2008\.Designing a common POS\-tagset framework for Indian languages\. In*Proceedings of the 6th workshop on Asian language resources*\.
- Sankaran et al\.\(2012\)Baskaran Sankaran, Majid Razmara, and Anoop Sarkar\. 2012\.Kriya \- An end\-to\-end Hierarchical Phrase\-based MT System\.*The Prague Bulletin of Mathematical Linguistics*97 \(05 2012\)\.[doi:10\.2478/v10108\-012\-0004\-y](https://doi.org/10.2478/v10108-012-0004-y)
- Santurkar et al\.\(2023\)Shibani Santurkar, Esin Durmus, Faisal Ladhak, Cinoo Lee, Percy Liang, and Tatsunori Hashimoto\. 2023\.Whose Opinions Do Language Models Reflect?arXiv:2303\.17548 \[cs\.CL\][https://arxiv\.org/abs/2303\.17548](https://arxiv.org/abs/2303.17548)
- Sarma et al\.\(2010a\)Shikhar Kr Sarma, Biswajit Brahma, Moromi Gogoi, and Mane Bala Ramchiary\. 2010a\.A wordnet for Bodo language: Structure and development\. In*Global Wordnet Conference \(GWC10\), Mumbai, India*\.
- Sarma et al\.\(2010b\)Shikhar Kr Sarma, R Medhi, M Gogoi, Utpal Saikia, et al\.2010b\.Foundation and structure of developing an Assamese WordNet\. In*Proceedings of 5th international conference of the global WordNet Association*\.
- Sarvam 1 \(2024\)Sarvam 1 2024\.Sarvam 1: The first Indian language LLM\.Accessed at[https://www\.sarvam\.ai/blogs/sarvam\-1](https://www.sarvam.ai/blogs/sarvam-1)\.\[Online; accessed 01\-June\-2026\]\.
- Sarvam\-M \(2025\)Sarvam\-M 2025\.Sarvam\-M: Explorations in Post Training and Inferencing Optimizations for a Hybrid Indic LLM\.Accessed at[https://www\.sarvam\.ai/blogs/sarvam\-m/](https://www.sarvam.ai/blogs/sarvam-m/)\.\[Online; accessed 01\-March\-2026\]\.
- Sarvam Translate \(2025\)Sarvam Translate 2025\.Sarvam\-Translate: an open\-weights model, supports translation across 22 Indian languages with structured long\-form text\.Accessed at[https://www\.sarvam\.ai/blogs/sarvam\-translate](https://www.sarvam.ai/blogs/sarvam-translate)\.\[Online; accessed 01\-March\-2026\]\.
- Saurav et al\.\(2020\)Kumar Saurav, Kumar Saunack, Diptesh Kanojia, and Pushpak Bhattacharyya\. 2020\.“A Passage to India”: Pre\-trained Word Embeddings for Indian Languages\. In*Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under\-resourced languages \(SLTU\) and Collaboration and Computing for Under\-Resourced Languages \(CCURL\)*, Dorothee Beermann, Laurent Besacier, Sakriani Sakti, and Claudia Soria \(Eds\.\)\. European Language Resources association, Marseille, France, 352–357\.[https://aclanthology\.org/2020\.sltu\-1\.49/](https://aclanthology.org/2020.sltu-1.49/)
- Sengupta and Chaudhuri \(1996\)Probal Sengupta and BB Chaudhuri\. 1996\.Morphological processing of Indian languages for lexical interaction with application to spelling error correction\.*Sadhana*21, 3 \(1996\), 363–380\.
- Sharma et al\.\(2008\)Utpal Sharma, Jugal K Kalita, and Rajib K Das\. 2008\.Acquisition of morphology of an Indic language from text corpus\.*ACM Transactions on Asian Language Information Processing \(TALIP\)*7, 3 \(2008\), 1–33\.
- Shrivastava et al\.\(2005\)Manish Shrivastava, Nitin Agrawal, Bibhuti Mohapatra, Smriti Singh, and Pushpak Bhattacharya\. 2005\.Morphology based natural language processing tools for Indian languages’\. In*Proceedings of the 4th Annual Inter Research Institute Student Seminar in Computer Science, IIT, Kanpur, India, April*\.
- Shrivastava and Bhattacharyya \(2008\)Manish Shrivastava and Pushpak Bhattacharyya\. 2008\.Hindi POS tagger using naive stemming: harnessing morphological information without extensive linguistic knowledge\. In*International Conference on NLP \(ICON08\), Pune, India*\.
- Singh et al\.\(2005\)Akshay Singh, Sushma Bendre, and Rajeev Sangal\. 2005\.HMM based chunker for Hindi\. In*Companion Volume to the Proceedings of Conference including Posters/Demos and tutorial abstracts*\.
- Singh and Singh \(2015\)Arvinder Singh and Parminder Singh\. 2015\.Punjabi dialects conversion system for Malwai and Doabi dialects\.*Indian Journal of Science and Technology*8, 27 \(2015\), 1–6\.
- Singh et al\.\(2008\)Anil Kumar Singh, Kiran Pala, and Harshit Surana\. 2008\.Estimating the Resource Adaption Cost from a Resource Rich Language to a Similar Resource Poor Language\.\. In*LREC*\.
- Sinha et al\.\(1995\)R\.M\.K\. Sinha, K\. Sivaraman, A\. Agrawal, R\. Jain, R\. Srivastava, and A\. Jain\. 1995\.ANGLABHARTI: a multilingual machine aided translation project on translation from English to Indian languages\. In*1995 IEEE International Conference on Systems, Man and Cybernetics\. Intelligent Systems for the 21st Century*, Vol\. 2\. 1609–1614 vol\.2\.[doi:10\.1109/ICSMC\.1995\.538002](https://doi.org/10.1109/ICSMC.1995.538002)
- Slade \(2016\)Benjamin Slade\. 2016\.Compound verbs\.*The University of Utah*\(2016\)\.
- Sourati et al\.\(2025\)Zhivar Sourati, Farzan Karimi\-Malekabadi, Meltem Ozcan, Colin McDaniel, Alireza Ziabari, Jackson Trager, Ala Tak, Meng Chen, Fred Morstatter, and Morteza Dehghani\. 2025\.The shrinking landscape of linguistic diversity in the age of large language models\.*arXiv preprint arXiv:2502\.11266*\(2025\)\.
- Srirampur and Chandibhamar \(2014\)Saikrishna Srirampur and Ravi Chandibhamar\. 2014\.Statistical Morph Analyzer \(SMA\+\+\) for Indian Languages\. 103–109\.[doi:10\.3115/v1/W14\-5312](https://doi.org/10.3115/v1/W14-5312)
- Srivastava and Bhat \(2013\)Rishabh Srivastava and Riyaz Ahmad Bhat\. 2013\.Transliteration systems across indian languages using parallel corpora\. In*Proceedings of the 27th Pacific Asia conference on language, information, and computation \(PACLIC 27\)*\. 390–398\.
- Srivatsa et al\.\(2026\)Sharath Srivatsa, M\. Aparna, Srinath Srinivasa, and T\. B\. Dinesh\. 2026\.Safeguarding Plurality: The Digital Preservation of Diverse Worldviews\. In*Big Data Analytics in Astronomy, Science, and Engineering*, Shelly Sachdeva, Yutaka Watanobe, and Subhash Bhalla \(Eds\.\)\. Springer Nature Switzerland, Cham, 268–282\.
- Srivatsa et al\.\(2024\)Sharath Srivatsa, Aparna M, Sai Madhavan G, and Srinath Srinivasa\. 2024\.Knowledge Management Framework Over Low Resource Indian Colloquial Language Audio Contents\. In*Proceedings of the 7th Joint International Conference on Data Science & Management of Data \(11th ACM IKDD CODS and 29th COMAD\)*\(Bangalore, India\)*\(CODS\-COMAD ’24\)*\. Association for Computing Machinery, New York, NY, USA, 553–557\.[doi:10\.1145/3632410\.3632483](https://doi.org/10.1145/3632410.3632483)
- Srivatsa et al\.\(2025\)Sharath Srivatsa, Aparna M, Malavika V, Samarth P, and Srinath Srinivasa\. 2025\.Parichaya: Rural Colloquial Knowledge AI Interface\. In*Proceedings of the 8th International Conference on Data Science and Management of Data \(12th ACM IKDD CODS and 30th COMAD\)**\(CODS\-COMAD ’24\)*\. Association for Computing Machinery, New York, NY, USA, 391–394\.[doi:10\.1145/3703323\.3704271](https://doi.org/10.1145/3703323.3704271)
- Surana and Singh \(2008\)Harshit Surana and Anil Kumar Singh\. 2008\.A more discerning and adaptable multilingual transliteration mechanism for indian languages\. In*Proceedings of the Third International Joint Conference on Natural Language Processing: Volume\-I*\.
- Thara and Poornachandran \(2018\)S Thara and Prabaharan Poornachandran\. 2018\.Code\-Mixing: A Brief Survey\. In*2018 International Conference on Advances in Computing, Communications and Informatics \(ICACCI\)*\. 2382–2388\.[doi:10\.1109/ICACCI\.2018\.8554413](https://doi.org/10.1109/ICACCI.2018.8554413)
- Tholpadi et al\.\(2017\)Goutham Tholpadi, Chiranjib Bhattacharyya, and Shirish Shevade\. 2017\.Corpus\-based translation induction in indian languages using auxiliary language corpora from Wikipedia\.*ACM Transactions on Asian and Low\-Resource Language Information Processing \(TALLIP\)*16, 3 \(2017\), 1–25\.
- Tripathi et al\.\(2025\)Kumud Tripathi, Raj Gothi, and Pankaj Wasnik\. 2025\.Enhancing whisper’s accuracy and speed for indian languages through prompt\-tuning and tokenization\. In*ICASSP 2025\-2025 IEEE International Conference on Acoustics, Speech and Signal Processing \(ICASSP\)*\. IEEE, 1–5\.
- UNICODE STANDARD For Indic Scripts \(\[n\. d\.\]\)UNICODE STANDARD For Indic Scripts \[n\. d\.\]\.UNICODE STANDARD For Indic Scripts\.https://www\.unicode\.org/L2/L2003/03102\-indic\-ov\.pdf\.
- V\. et al\.\(2009\)Dhanalakshmi V\., Padmavathy P\., Anand Kumar M\., Soman K\.P\., and Rajendran S\. 2009\.Chunker for Tamil\. In*2009 International Conference on Advances in Recent Technologies in Communication and Computing*\. 436–438\.[doi:10\.1109/ARTCom\.2009\.191](https://doi.org/10.1109/ARTCom.2009.191)
- Vijayanand et al\.\(2002\)K\. Vijayanand, S\.I\. Choudhury, and P\. Ratna\. 2002\.VAASAANUBAADA: automatic machine translation of bilingual Bengali\-Assamese news texts\. In*Language Engineering Conference, 2002\. Proceedings*\. 183–188\.[doi:10\.1109/LEC\.2002\.1182307](https://doi.org/10.1109/LEC.2002.1182307)
- Vikram and Urs \(2007\)T\. N\. Vikram and Shalini R\. Urs\. 2007\.Development of Prototype Morphological Analyzer for he South Indian Language of Kannada\. In*Asian Digital Libraries\. Looking Back 10 Years and Forging New Frontiers*, Dion Hoe\-Lian Goh, Tru Hoang Cao, Ingeborg Torvik Sølvberg, and Edie Rasmussen \(Eds\.\)\. Springer Berlin Heidelberg, Berlin, Heidelberg, 109–116\.
- Visweswariah et al\.\(2011\)Karthik Visweswariah, Rajakrishnan Rajkumar, Ankur Gandhe, Ananthakrishnan Ramanathan, and Jiri Navratil\. 2011\.A Word Reordering Model for Improved Machine Translation\. In*Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing*, Regina Barzilay and Mark Johnson \(Eds\.\)\. Association for Computational Linguistics, Edinburgh, Scotland, UK\., 486–496\.[https://aclanthology\.org/D11\-1045/](https://aclanthology.org/D11-1045/)
- Wendler et al\.\(2024\)Chris Wendler, Veniamin Veselovsky, Giovanni Monea, and Robert West\. 2024\.Do Llamas Work in English? On the Latent Language of Multilingual Transformers\. In*Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics \(Volume 1: Long Papers\)*, Lun\-Wei Ku, Andre Martins, and Vivek Srikumar \(Eds\.\)\. Association for Computational Linguistics, Bangkok, Thailand, 15366–15394\.[doi:10\.18653/v1/2024\.acl\-long\.820](https://doi.org/10.18653/v1/2024.acl-long.820)
- Xue et al\.\(2020\)Linting Xue, Noah Constant, Adam Roberts, Mihir Kale, Rami Al\-Rfou, Aditya Siddhant, Aditya Barua, and Colin Raffel\. 2020\.mT5: A massively multilingual pre\-trained text\-to\-text transformer\.*CoRR*abs/2010\.11934 \(2020\)\.arXiv:2010\.11934[https://arxiv\.org/abs/2010\.11934](https://arxiv.org/abs/2010.11934)
- Zydenbos \(2020\)Robert J Zydenbos\. 2020\.*A Manual of Modern Kannada*\.CrossAsia E\-Publishing\.[https://doi\.org/10\.11588/xabooks\.736](https://doi.org/10.11588/xabooks.736)\.