information-retrieval

Tag

Cards List
#information-retrieval

Tevatron-Elastic: A Unified Abstraction for Training Elastic Retrievers and Rerankers

arXiv cs.CL · yesterday Cached

Tevatron-Elastic presents a unified abstraction for training elastic retrievers and rerankers, enabling a single checkpoint to serve multiple model sizes across depth, token, and width axes. It generalizes prior methods like Matryoshka embeddings and early exit, and introduces Matryoshka LTC for joint token-compression training.

0 favorites 0 likes
#information-retrieval

SPIEval: Evaluating Large Language Models as Mobile Assistants over Scattered Personal Information

Hugging Face Daily Papers · yesterday Cached

SPIEval is a human-curated benchmark for evaluating LLMs as mobile assistants on scattered personal information tasks, covering 250 tasks across 10 apps. It reveals that even the best model, GPT-5.5 (xhigh), achieves only 57.3% accuracy, with most failures due to inaccurate information localization and insufficient verification.

0 favorites 0 likes
#information-retrieval

Factorized Hypothesis Search for Evidence-to-Taxonomy Retrieval

arXiv cs.CL · 2d ago Cached

This paper introduces Factorized Hypothesis Search (FHS), a method for retrieving concepts from large taxonomies when inputs provide indirect contextual evidence, such as table cells or clinical notes. FHS achieves strong results on financial taxonomy tagging and CodiEsp clinical coding, outperforming non-oracle baselines in Recall@1, MRR, and accuracy.

0 favorites 0 likes
#information-retrieval

TourSynbio-Search: A Large Language Model Driven Agent Framework for Unified Search Method for Protein Engineering

arXiv cs.AI · 6d ago Cached

The paper presents TourSynbio-Search, an LLM-driven agent framework for unified protein engineering search across literature and biological databases, powered by the TourSynbio-7B multimodal model with dual PaperSearch and ProteinSearch components.

0 favorites 0 likes
#information-retrieval

LegalPincite: Multi-level Legal Information Retrieval Dataset

Hugging Face Daily Papers · 2026-08-04 Cached

Introduces LegalPincite, a large-scale legal information retrieval dataset built from CJEU judgments, featuring masked queries, full corpora, and paragraph-level citation annotations to enable multi-level retrieval evaluation.

0 favorites 0 likes
#information-retrieval

IFCMemoryBench: Evaluating Long-Term Memory of LLM-Based Agents in BIM Information Retrieval

arXiv cs.AI · 2026-07-31 Cached

This paper introduces IFCMemoryBench, a human-validated benchmark for evaluating long-term memory in LLM-based agents for BIM information retrieval. It shows that current memory systems achieve only 32.4% answer accuracy, revealing a domain-transfer gap in agent memory.

0 favorites 0 likes
#information-retrieval

GuidedRAG: Semantic Steering of Retrieval-Augmented Generation

arXiv cs.AI · 2026-07-31 Cached

GuidedRAG is a research paper proposing a novel RAG extension that adds a semantics-based selection stage before retrieval, improving retrieval relevance and reducing overhead across diverse RAG variants.

0 favorites 0 likes
#information-retrieval

Which RAG Paradigm Wins at Scale? A Scaling Study of Retrieval-Augmented Generation Paradigms

arXiv cs.CL · 2026-07-30 Cached

This paper presents a controlled scaling study comparing lexical, dense, graph-based, and agentic RAG paradigms across corpus sizes from 1,000 to 512,000 documents, finding that BM25 provides the best accuracy-cost tradeoff, while graph-based RAG faces high construction costs that limit scalability.

0 favorites 0 likes
#information-retrieval

The Effect of Text Chunk Size on Retrieval-Augmented Generation Performance

arXiv cs.CL · 2026-07-29 Cached

This paper investigates how the size of text chunks (sentences, paragraphs, chapters) in Retrieval-Augmented Generation systems affects generation quality, retrieval precision, and computational efficiency, using identical textbooks segmented at different granularities.

0 favorites 0 likes
#information-retrieval

Understanding Semantic IDs: From Item Representation to Item Selection in Generative Recommendation

arXiv cs.AI · 2026-07-29 Cached

This paper systematically investigates Semantic IDs (SIDs) in generative recommendation, finding that while SIDs preserve coarse item organization, they lose fine local structure from the encoder. The authors propose Item-Supported Decoding (ISD), a lightweight inference-time method that improves NDCG@10 by up to 31.2% without additional parameters or retraining.

0 favorites 0 likes
#information-retrieval

@awscloud: 58% of employees lose 2 hours a day just searching for information. That's 10 hours a week gone before real work starts…

X AI KOLs Timeline · 2026-07-28 Cached

AWS highlights that 58% of employees lose 2 hours daily searching for information, and promotes Amazon Quick as a solution to reclaim lost time.

0 favorites 0 likes
#information-retrieval

Optimizing Hypergraph-Based RAG: Toward Better Fact Extraction and Chunk Retrieval

arXiv cs.AI · 2026-07-24 Cached

This paper proposes improvements to HyperGraphRAG by using self-consistency prompting for better fact extraction and Personalized PageRank for enhanced chunk retrieval.

0 favorites 0 likes
#information-retrieval

NOWJ@COLIEE 2026: Adaptive Pipelines for Legal Retrieval and Reasoning

arXiv cs.CL · 2026-07-21 Cached

This paper presents adaptive pipelines for legal retrieval, entailment, and judgment prediction tasks in the COLIEE 2026 competition, using multi-stage retrieval, reranking, and LLM-based reasoning.

0 favorites 0 likes
#information-retrieval

AutoIndex: Learning Representation Programs for Retrieval

Hugging Face Daily Papers · 2026-07-21 Cached

AutoIndex is a framework that learns executable representation programs to transform documents before indexing, improving retrieval quality over static BM25 baselines by average 8.4% Recall@100 and 8.3% nDCG@10.

0 favorites 0 likes
#information-retrieval

Quantifying and Expanding the Theoretical Capacity of Late-Interaction Retrieval Models

Hugging Face Daily Papers · 2026-07-07 Cached

This paper quantifies and expands the theoretical capacity of late-interaction retrieval models, showing that MaxSim can replicate inner products between non-negative vectors and proposing Signed MaxSim for arbitrary real-valued vectors, revealing a representation gap between inner product and late-interaction models.

0 favorites 0 likes
#information-retrieval

@SaitoWu: Highly recommend WorkBuddy users install this podcast info source: https://github.com/hardhackerlabs/podwise-cli… It's super convenient: search any podcast, fetch structured summaries, key insights, Mind Map, and feed directly into Work…

X AI KOLs Timeline · 2026-07-04 Cached

The recommended podwise-cli is a CLI tool that converts any podcast content into structured summaries, key insights, and mind maps, making it convenient for AI agents and workflows.

0 favorites 0 likes
#information-retrieval

Libra: Training the Environment for Agentic Information Retrieval

arXiv cs.AI · 2026-07-02 Cached

The paper presents Libra, a self-evolving framework that introduces mutable catalogs into repositories to improve code localization for LLM agents, achieving logarithmic improvements and zero-shot transfer across different models and problem sets.

0 favorites 0 likes
#information-retrieval

Why Advanced Encoders Lag on Sparse Retrieval? The Answer and an Approach to Bridging Vocabulary Gaps

arXiv cs.AI · 2026-07-02 Cached

This paper identifies a vocabulary gap as the root cause why advanced encoders like ModernBERT underperform in learned sparse retrieval, and proposes Vocabulary Transfer (VT), a model-agnostic framework that migrates encoders to sparse-friendly vocabularies, achieving state-of-the-art on the BEIR benchmark.

0 favorites 0 likes
#information-retrieval

Bayesian Uncertainty Propagation for Agentic RAG Pipelines: A Proof-of-Concept Study on Multi-Hop Question Answering

arXiv cs.AI · 2026-07-02 Cached

This paper presents a Bayesian uncertainty propagation framework for Agentic RAG systems, evaluating it on multi-hop QA benchmarks with GPT models, showing promise for monitoring reliability in industrial decision support.

0 favorites 0 likes
#information-retrieval

Multi-Turn Agentic Scientific Literature Search via Workflow Induction

arXiv cs.CL · 2026-07-02 Cached

This paper introduces PaperPilot, a multi-turn literature search agent that constructs executable DAGs of search operators and refines workflows through user feedback, achieving significant improvements in retrieval metrics over baseline models.

0 favorites 0 likes
Next →
← Back to home

Submit Feedback