Tag
CiteVQA is a benchmark for document vision-language models that evaluates both answer correctness and citation of supporting evidence, revealing widespread attribution hallucinations where models provide correct answers but cite wrong regions.
DocScope is a new benchmark for evaluating the verifiable reasoning and trustworthiness of Multimodal Large Language Models on long documents, introducing a four-stage evaluation protocol for page localization, region grounding, fact extraction, and answer verification.
DocAtlas is a framework that creates high-fidelity OCR datasets and benchmarks across 82 languages, using differential rendering and synthetic generation. It demonstrates that Direct Preference Optimization improves multilingual model adaptation without degrading base-language performance.
NuExtract3 is a 4B vision-language reasoning model for document understanding, enabling structured extraction and image-to-Markdown conversion.
ParseBench introduces the first benchmark evaluating vision-language models on chart comprehension within full enterprise documents, addressing gaps in prior chart-only benchmarks.
dots.ocr is a new lightweight 1.7B parameter multilingual vision-language model that achieves state-of-the-art performance on OmniDocBench, outperforming much larger models (72B+) at document parsing and OCR tasks.
IBM releases Granite 4.0 3B Vision, a compact vision-language model designed for enterprise document understanding, featuring specialized capabilities for table extraction, chart interpretation via ChartNet, and key-value pair grounding.
This paper introduces CommonForms, a large-scale, diverse dataset for form field detection, along with FFDNet models that achieve high precision on form field detection tasks. The dataset, models, and code are open-sourced.
RAGFlow is an open-source RAG engine by Infiniflow that uses deep document understanding to extract and organize knowledge from documents, enabling reliable retrieval-augmented generation with support for various LLMs and self-hosting.