mlsanityData to 14 Oct 2026

HiChunk: Evaluating and Enhancing Retrieval-Augmented Generation with Hierarchical Chunking

arXiv 2509.11552 ↗First posted 15 Sep 2025cs.CL cs.AIcited by 12

On the map: Retrieval-augmented generation → Multimodal RAG

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) enhances the response capabilities of language models by integrating external knowledge sources. However, document chunking as an important part of RAG system often lacks effective evaluation tools. This paper first analyzes why existing RAG evaluation benchmarks are inadequate for assessing document chunking quality, specifically due to evidence sparsity. Based on this conclusion, we propose HiCBench, which includes manually annotated multi-level document chunking points, synthesized evidence-dense quetion answer(QA) pairs, and their corresponding evidence sources. Additionally, we introduce the HiChunk framework, a multi-level document structuring framework based on fine-tuned LLMs, combined with the Auto-Merge retrieval algorithm to improve retrieval quality. Experiments demonstrate that HiCBench effectively evaluates the impact of different chunking methods across the entire RAG pipeline. Moreover, HiChunk achieves better chunking quality within reasonable time consumption, thereby enhancing the overall performance of RAG systems.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation. Builds on 28 of its 40 references that are in the map. First posted on arXiv 15 Sep 2025.

Builds on

28 of 40 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Rethinking Chunk Size For Long-Document Retrieval: A Multi-Dataset Analysis27 May
  2. 2025MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System12 Mar
  3. 2024OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation3 Dec

Other references · 25

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  5. 2023LongBench: A Bilingual, Multitask Benchmark for Long Context Understandingcited by 1,417
  6. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
  7. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 698
  8. 2017The NarrativeQA Reading Comprehension Challengecited by 597
  9. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 578
  10. 2021A Dataset of Information-Seeking Questions and Answers Anchored in Research Paperscited by 486
  11. 2021Efficient Attentions for Long Document Summarizationcited by 345
  12. 2023Benchmarking Large Language Models in Retrieval-Augmented Generationcited by 312
13 more
  1. 2021QuALITY: Question Answering with Long Input Texts, Yes!cited by 208
  2. 2023Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificitycited by 206
  3. 2022Rethinking with Retrieval: Faithful Large Language Model Inferencecited by 145
  4. 2024RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systemscited by 117
  5. 2018Text Segmentation as a Supervised Learning Taskcited by 76
  6. 2024Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Modelscited by 73
  7. 2023Are ChatGPT and GPT-4 General-Purpose Solvers for Financial Text Analytics? A Study on Several Typical Taskscited by 59
  8. 2025When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generationcited by 48
  9. 2024LumberChunker: Long-Form Narrative Document Segmentationcited by 36
  10. 2022Toward Unifying Text Segmentation and Long Document Summarizationcited by 28
  11. 2021End-to-End Segmentation-based News Summarizationcited by 16
  12. 2021Sequence Model with Self-Adaptive Sliding Window for Efficient Spoken Document Segmentationcited by 14
  13. 2021VT-SSum: A Benchmark Dataset for Video Transcript Segmentation and Summarizationcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 9.

12 papers.

  1. 2025LAD-RAG: Layout-aware Dynamic RAG for Visually-Rich Document Understandingcited by 7
  2. 2026Taxonomy of the Retrieval System Framework: Pitfalls and Paradigmscited by 4
  3. 2026A Systematic Investigation of Document Chunking Strategies and Embedding Sensitivitycited by 3
  4. 2026LingDT-VL-OCR: Structure-Aware Document-Level Parsing with Fine-Grained Visual Referencecited by 2
  5. 2026Chunking Methods on Retrieval-Augmented Generation - Effectiveness Evaluation Against Computational Cost and Limitationscited by 1
  6. 2025Less is More: Denoising Knowledge Graphs For Retrieval Augmented Generationcited by 0
  7. 2025M'as contexto no es mejor. Paradoja de la diluci'on vectorial en RAG corporativoscited by 0
  8. 2026Qwen Goes Brrr: Off-the-Shelf RAG for Ukrainian Multi-Domain Document Understandingcited by 0
  9. 2026LongDocBench: Benchmarking TOC Hierarchy and Contextual Relationship Recovery in Long Documentscited by 0
  10. 2026Parser, Chunking, and Embedding Interactions in Retrieval-Augmented Generation over Indian Government Regulatory Documentscited by 0
  11. 2026Investigating the Role of Reasoning-Language Alignment in Monolingual Retrieval-Augmented Generationcited by 0
  12. 2026Verifiable Retrieval for Legal Reasoning through Structure-driven Knowledge Graphcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Is Semantic Chunking Worth the Computational Cost?
  2. 2026CHOP: Chunkwise Context-Preserving Framework for RAG on Multi Documents
  3. 2025A New HOPE: Domain-agnostic Automatic Evaluation of Text Chunking
  4. 2024ChunkRAG: Novel LLM-Chunk Filtering Method for RAG Systems
  5. 2026Adaptive Chunking: Optimizing Chunking-Method Selection for RAG
  6. 2026Evaluating Chunking Strategies for Retrieval-Augmented Generation on Academic Texts
  7. 2025SmartChunk Retrieval: Query-Aware Chunk Compression with Planning for Efficient Document RAG
  8. 2025Enhancing Retrieval Augmented Generation with Hierarchical Text Segmentation Chunking