Overview

Document chunking studies how to divide long or complex documents into units that models can retrieve, understand, and process without losing important context. Common approaches include fixed-token or recursive splitting, semantic boundaries, and structure-aware methods that preserve sections, tables, or document hierarchies; newer methods adapt boundaries to likely queries. Evaluations commonly measure retrieval and question-answering quality alongside index size, latency, and token use, and show that parsing and embedding choices interact with chunking. There is no universally best strategy: preserving structure and cross-section evidence can improve results, but may increase cost, while benefits vary by domain, document layout, and task.

Latest papers

CardsList

54 papers4 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

  1. Calibrating Document-Local Boundaries for Contextual Chunk Retrieval

    Nov 9, 2026Yuanxiang Wang, Hui Jiang, Da Zhu +1Document ChunkingContrastive Learning

  2. QESChunker: A Single Objective Unifies Overlapping and Non-Overlapping Chunking for RAG

    Oct 27, 2026Yifan Zhao, Qianyang Zhao, Xinyu Guan +2Document ChunkingRetrieval-Augmented Generation

  3. Chunk Recomputation under Real Document Revisions: Measuring Update Cost and Retrieval Quality of Fixed, Recursive, and Content-Defined Chunking

    Oct 22, 2026Yuning Bian, Lele Xu, Yifan Yuan +2Document ChunkingRAG Evaluation

  4. StrucChunk: Structure-Aware Retrieval for Legal Document RAG

    Oct 19, 2026Surya Deep Singh, Ashutosh Tripathi, Gaurav Deep SinghLegal IRDocument Chunking

  5. Does Document Structure Help Dense Retrieval? A Placebo-Controlled Ablation of Four Mechanisms Across Two Corpora

    Oct 7, 2026Andrey Kuehlkamp, Priscila Correa Saboia Moreira, Samuel RundInformation RetrievalDense Retrieval

  6. Smart Content Ingestion for Generative AI Workloads

    Oct 5, 2026Abbas Raza Ali, Muhammad Ajmal Siddiqui, Moona ZahidDocument ChunkingDocument Information Extraction

  7. Splitting Documents at Lower Cost: Multi-Split Boundary Decisions for LLM-Based Page Stream Segmentation

    Sep 18, 2026Nikhil Reddy Pottanigari, Sepideh Kharaghani, Saverio Vadacchino +2Document ChunkingLLM Inference Efficiency

  8. Q&A on Any Spreadsheet Requires Interpreting Its Grid Structure

    Sep 17, 2026Zofia SmoleńDocument ChunkingTable QA

  9. Doc2FRC: Length-Consistent Document-Level Machine Translation via Fixed-Range Chunking

    Sep 11, 2026Xiaotian Wang, Youyuan Lin, Zhan Shen +1Document ChunkingLLM Fine-Tuning

  10. EAR: Entity-Aware Partitioning Approach for Retrieval-Augmented Generation Development

    Sep 10, 2026Cenab Batu Bora, Oylum Alatlı, Sebnem Bora +1Document ChunkingRetrieval-Augmented Generation

  11. Configurable Semantic Chunking for Biomedical Information Extraction in Retrieval-Augmented Generation

    Aug 31, 2026Riya Ahuja, Tim Kacprowski, Roya Shiasi SardoabiRelation ExtractionDocument Chunking

  12. When Tokenizers Fail: Byte-Level Chunking for Zero-Shot Transfer to Low-Resource Languages

    Aug 27, 2026Sanjeev Kumar, Atsuki Yamaguchi, Nikolaos AletrasByte-Level Language ModelLow-Resource Language Processing

  13. Comparing Chunking and Embedding Strategies for Turkish RAG Systems

    Aug 24, 2026Mustafa Sertaç Türkel, Fatma Nur Korkmaz, Ahmet Tuğrul BayrakRetrieval-Augmented GenerationRAG Evaluation

  14. Khondo: A Multimodal Benchmark for Document Packet Splitting of Bangla Forms

    Jul 23, 2026Abu Tyeb Azad, Fahim Ahmed, Ishita Sur Apan +7Document ChunkingMultilingual VLM Evaluation

  15. Evaluating Chunking Strategies for Retrieval-Augmented Generation on Academic Texts

    Jul 2, 2026Valentin J. J. Kreileder, Johannes Reisinger, Andreas FischerDocument ChunkingRetrieval-Augmented Generation

  16. When Does Overlap Help? OSU-Mem and a Cell-Conditional Analysis of Trajectory Memory for LLM Agents

    Jun 19, 2026Mellow Baixuan Chen, Xiangguo SunDocument ChunkingLLM Agent Memory

  17. Lost in a Single Vector: Improving Long-Document Retrieval with Chunk Evidence Aggregation

    Jun 17, 2026Shanshan Lyu, Yiwei Wang, Yujun Cai +2Long-Context RetrievalDocument Chunking

  18. SproutRAG: Attention-Guided Tree Search with Progressive Embeddings for Long-Document RAG

    Jun 16, 2026Amirhossein Abaskohi, Issam H. Laradji, Peter West +1Document ChunkingRetrieval-Augmented Generation

  19. Efficient RAG with Intent-Aware Retrieval and Semantics-Preserving Chunking

    May 31, 2026Fachrina Dewi Puspitasari, Chaoning Zhang, Jiaquan Zhang +6Multi-Hop QADocument Chunking

  20. Chunking Methods on Retrieval-Augmented Generation - Effectiveness Evaluation Against Computational Cost and Limitations

    May 30, 2026Mateusz Śmigielski, Michał Rajkowski, Mateusz Zbrocki +5Document ChunkingRetrieval-Augmented Generation

  21. Adaptive Targeted Dynamic Chunking for Tokenization-Free Hierarchical Model

    May 28, 2026Thang Dang, Akira Nakagawa, Kenichi Kobayashi +1Document ChunkingByte-Level Language Model

  22. LitSeg: Narrative-Aware Document Segmentation for Literary RAG

    May 26, 2026Ruikang Zhang, Zhanni Chen, Yiqiao Cai +1Document ChunkingRetrieval-Augmented Generation

  23. SEEK: Semantic Evidence Extraction via Adaptive ChunKing for Multilingual Fact-Checking

    May 26, 2026Gaurav Kumar, Babu Kumar, Ayush Garg +2Document ChunkingAutomated Fact-Checking

  24. Evaluation of Chunking Strategies for Effective Text Embedding in Low-Resource Language on Agricultural Documents

    May 21, 2026Sovandara Chhoun, Pichdara Po, Sereiwathna Ros +2Document ChunkingMultilingual IR