Image de couverture de livre

Rethinking Chunk Size For Long-Document Retrieval: A Multi-Dataset Analysis

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Bhat, Sinchana Ramakanth, Rudat, Max, Spiekermann, Jannis, Flores-Herr, Nicolas
Format:	Preprint
Publié:	2025
Sujets:	Information Retrieval
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Towards End-to-End Model-Agnostic Explanations for RAG Systems
par: Sudhi, Viju, et autres
Publié: (2025)

Beyond Chunk-Then-Embed: A Comprehensive Taxonomy and Evaluation of Document Chunking Strategies for Information Retrieval
par: Zhou, Yongjie, et autres
Publié: (2026)

Fact Finder -- Enhancing Domain Expertise of Large Language Models by Incorporating Knowledge Graphs
par: Steinigen, Daniel, et autres
Publié: (2024)

Beyond Chunking: Discourse-Aware Hierarchical Retrieval for Long Document Question Answering
par: Chen, Huiyao, et autres
Publié: (2025)

Revisiting Document-Level Relation Extraction with Context-Guided Link Prediction
par: Jain, Monika, et autres
Publié: (2024)

Evaluating Chunking Strategies For Retrieval-Augmented Generation in Oil and Gas Enterprise Documents
par: Taiwo, Samuel, et autres
Publié: (2026)

Cross-Document Topic-Aligned Chunking for Retrieval-Augmented Generation
par: Stankovic, Mile
Publié: (2025)

Knowledge-Driven Cross-Document Relation Extraction
par: Jain, Monika, et autres
Publié: (2024)

SmartChunk Retrieval: Query-Aware Chunk Compression with Planning for Efficient Document RAG
par: Zhang, Xuechen, et autres
Publié: (2025)

Visual Late Chunking: An Empirical Study of Contextual Chunking for Efficient Visual Document Retrieval
par: Yan, Yibo, et autres
Publié: (2026)

Chunk Knowledge Generation Model for Enhanced Information Retrieval: A Multi-task Learning Approach
par: Kim, Jisu, et autres
Publié: (2025)

A Survey of Long-Document Retrieval in the PLM and LLM Era
par: Li, Minghan, et autres
Publié: (2025)

Toward General Semantic Chunking: A Discriminative Framework for Ultra-Long Documents
par: Wu, Kaifeng, et autres
Publié: (2025)

Rethinking the Role of Token Retrieval in Multi-Vector Retrieval
par: Lee, Jinhyuk, et autres
Publié: (2023)

On the Reproducibility of Learned Sparse Retrieval Adaptations for Long Documents
par: Lionis, Emmanouil Georgios, et autres
Publié: (2025)

Structure-Aware Chunking for Tabular Data in Retrieval-Augmented Generation
par: Guttal, Pooja, et autres
Publié: (2026)

AnnoRetrieve: Efficient Structured Retrieval for Unstructured Document Analysis
par: Lin, Teng, et autres
Publié: (2026)

ModernVBERT: Towards Smaller Visual Document Retrievers
par: Teiletche, Paul, et autres
Publié: (2025)

Graph-Aware Late Chunking for Retrieval-Augmented Generation in Biomedical Literature
par: Mortezaagha, Pouria, et autres
Publié: (2026)

Chunking, Retrieval, and Re-ranking: An Empirical Evaluation of RAG Architectures for Policy Document Question Answering
par: Maharjan, Anuj, et autres
Publié: (2026)

AttentionRetriever: Attention Layers are Secretly Long Document Retrievers
par: Fu, David Jiahao, et autres
Publié: (2026)

Web Retrieval-Aware Chunking (W-RAC) for Efficient and Cost-Effective Retrieval-Augmented Generation Systems
par: Allu, Uday, et autres
Publié: (2026)

DocMMIR: A Framework for Document Multi-modal Information Retrieval
par: Li, Zirui, et autres
Publié: (2025)

Beyond Chunks and Graphs: Retrieval-Augmented Generation through Triplet-Driven Thinking
par: Gong, Shengbo, et autres
Publié: (2025)

Budget-Constrained Online Retrieval-Augmented Generation: The Chunk-as-a-Service Model
par: Al-Maliki, Shawqi, et autres
Publié: (2026)

A Systematic Analysis of Chunking Strategies for Reliable Question Answering
par: Bennani, Sofia, et autres
Publié: (2026)

User Long-Term Multi-Interest Retrieval Model for Recommendation
par: Meng, Yue, et autres
Publié: (2025)

Grounding Language Model with Chunking-Free In-Context Retrieval
par: Qian, Hongjin, et autres
Publié: (2024)

The Chronicles of RAG: The Retriever, the Chunk and the Generator
par: Finardi, Paulo, et autres
Publié: (2024)

S2 Chunking: A Hybrid Framework for Document Segmentation Through Integrated Spatial and Semantic Analysis
par: Verma, Prashant
Publié: (2025)

LongRetriever: Towards Ultra-Long Sequence based Candidate Retrieval for Recommendation
par: Ren, Qin, et autres
Publié: (2025)

Query-Adaptive Semantic Chunking for Retrieval-Augmented Generation: A Dynamic Strategy with Contextual Window Expansion
par: Rastogi, Mudit
Publié: (2026)

Rethinking Retrieval-Augmentation as Synthesis: A Query-Aware Context Merging Approach
par: Guo, Jiarui, et autres
Publié: (2026)

Act-With-Think: Chunk Auto-Regressive Modeling for Generative Recommendation
par: Wang, Yifan, et autres
Publié: (2025)

ClimRetrieve: A Benchmarking Dataset for Information Retrieval from Corporate Climate Disclosures
par: Schimanski, Tobias, et autres
Publié: (2024)

CURE: A Dataset for Clinical Understanding & Retrieval Evaluation
par: Sheikh, Nadia Athar, et autres
Publié: (2024)

Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation
par: Merola, Carlo, et autres
Publié: (2025)

StratRAG: A Multi-Hop Retrieval Evaluation Dataset for Retrieval-Augmented Generation Systems
par: Patodiya, Aryan
Publié: (2026)

Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking
par: Jin, Haoxiang, et autres
Publié: (2025)

Rethinking Agentic RAG: Toward LLM-Driven Logical Retrieval Beyond Embeddings
par: Zeng, Yuqi, et autres
Publié: (2026)