# Meta-Chunking: Learning Text Segmentation and Semantic Completion via Logical Perception

arXiv: https://arxiv.org/abs/2410.12788 · HTML: https://mlsanity.com/paper/2410.12788/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 27 of its 44 references that are in the map.
- First posted on arXiv 16 Oct 2024.

## Placed in

- Retrieval-augmented generation / [Multimodal RAG](https://mlsanity.com/rag/multimodal-rag/)

## Builds on (most cited first, 27 of 27)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023)
- [MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries](https://mlsanity.com/paper/2401.15391/) (2024)
- [Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models](https://mlsanity.com/paper/2311.09210/) (2023)
- [A Survey on Retrieval-Augmented Text Generation](https://mlsanity.com/paper/2202.01110/) (2022)
- [Rethinking with Retrieval: Faithful Large Language Model Inference](https://mlsanity.com/paper/2301.00303/) (2022)
- [Internet-augmented language models through few-shot prompting for open-domain question answering](https://mlsanity.com/paper/2203.05115/) (2022)
- [To Believe or Not to Believe Your LLM](https://mlsanity.com/paper/2406.02543/) (2024)
- [Dense X Retrieval: What Retrieval Granularity Should We Use?](https://mlsanity.com/paper/2312.06648/) (2023)
- [DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Models](https://mlsanity.com/paper/2403.10081/) (2024)
- [Are ChatGPT and GPT-4 General-Purpose Solvers for Financial Text Analytics? A Study on Several Typical Tasks](https://mlsanity.com/paper/2305.05862/) (2023)
- [CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models](https://mlsanity.com/paper/2401.17043/) (2024)
- [Internal Consistency and Self-Feedback in Large Language Models: A Survey](https://mlsanity.com/paper/2407.14507/) (2024)
- [Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Models](https://mlsanity.com/paper/2407.04121/) (2024)
- [In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPT](https://mlsanity.com/paper/2304.08979/) (2023)
- [LumberChunker: Long-Form Narrative Document Segmentation](https://mlsanity.com/paper/2406.17526/) (2024)
- [EfficientRAG: Efficient Retriever for Multi-Hop Question Answering](https://mlsanity.com/paper/2408.04259/) (2024)
- [Analysing the Robustness of Dual Encoders for Dense Retrieval Against Misspellings](https://mlsanity.com/paper/2205.02303/) (2022)
- [Adaptive Contrastive Decoding in Retrieval-Augmented Generation for Handling Noisy Contexts](https://mlsanity.com/paper/2408.01084/) (2024)
- [Multi-Head RAG: Solving Multi-Aspect Problems with LLMs](https://mlsanity.com/paper/2406.05085/) (2024)
- [Sequence Model with Self-Adaptive Sliding Window for Efficient Spoken Document Segmentation](https://mlsanity.com/paper/2107.09278/) (2021)
- [ChatGPT Hallucinates when Attributing Answers](https://mlsanity.com/paper/2309.09401/) (2023)
- [BERM: Training the Balanced and Extractable Representation for Matching to Improve Generalization Ability of Dense Retrieval](https://mlsanity.com/paper/2305.11052/) (2023)
- [TegTok: Augmenting Text Generation via Task-specific and Open-world Knowledge](https://mlsanity.com/paper/2203.08517/) (2022)

## Built on by (most cited first, 17 of 17)

- [LightMem: Lightweight and Efficient Memory-Augmented Generation](https://mlsanity.com/paper/2510.18866/) (2025)
- [Chain-of-Memory: Lightweight Memory Construction with Dynamic Evolution for LLM Agents](https://mlsanity.com/paper/2601.14287/) (2026)
- [A Systematic Investigation of Document Chunking Strategies and Embedding Sensitivity](https://mlsanity.com/paper/2603.06976/) (2026)
- [Semantics Delivery Network: Rethinking Web Retrieval Infrastructure for LLM Agents](https://mlsanity.com/paper/2609.22486/) (2026)
- [Equipping Retrieval-Augmented Large Language Models with Document Structure Awareness](https://mlsanity.com/paper/2510.04293/) (2025)
- [Chunking Methods on Retrieval-Augmented Generation - Effectiveness Evaluation Against Computational Cost and Limitations](https://mlsanity.com/paper/2606.00881/) (2026)
- [Right Reset: Chunking by Prefix Removal](https://mlsanity.com/paper/2608.04330/) (2026)
- [From Evidence-Based Medicine to Knowledge Graph: Retrieval-Augmented Generation for Sports Rehabilitation and a Domain Benchmark](https://mlsanity.com/paper/2601.00216/) (2026)
- [Clinical Document Metadata Extraction: A Scoping Review](https://mlsanity.com/paper/2601.09730/) (2025)
- [MDKeyChunker: Single-Call LLM Enrichment with Rolling Keys and Key-Based Restructuring for High-Accuracy RAG](https://mlsanity.com/paper/2603.23533/) (2026)
- [LitSeg: Narrative-Aware Document Segmentation for Literary RAG](https://mlsanity.com/paper/2605.27156/) (2026)
- [SproutRAG: Attention-Guided Tree Search with Progressive Embeddings for Long-Document RAG](https://mlsanity.com/paper/2606.18381/) (2026)
- [MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level Retrieval](https://mlsanity.com/paper/2606.18508/) (2026)
- [SeKV: Resolution-Adaptive KV Cache with Hierarchical Semantic Memory for Long-Context LLM Inference](https://mlsanity.com/paper/2606.31145/) (2026)
- [CTRAG: An In-Context Retrieval-based Framework for Automated Compliance Checking using LLMs](https://mlsanity.com/paper/2608.02472/) (2026)
- [Doc2FRC: Length-Consistent Document-Level Machine Translation via Fixed-Range Chunking](https://mlsanity.com/paper/2609.12674/) (2026)
- [Beyond Similarity through Zero-Token Geometric Graphs for Multi-Hop RAG](https://mlsanity.com/paper/2609.19622/) (2026)

## Abstract (arXiv)

While Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for boosting large language models (LLMs) in knowledge-intensive tasks, it often overlooks the crucial aspect of text chunking within its workflow. This paper proposes the Meta-Chunking framework, which specifically enhances chunking quality through a dual strategy that identifies optimal segmentation points and preserves global information. Initially, breaking limitations of similarity-based chunking, we design two adaptive chunking techniques based on uncertainty, namely Perplexity Chunking and Margin Sampling Chunking, by utilizing the logical perception capabilities of LLMs. Given the inherent complexity across different texts, we integrate meta-chunk with dynamic merging, striking a balance between fine-grained and coarse-grained text chunking. Furthermore, we establish the global information compensation mechanism, encompassing a two-stage hierarchical summary generation process and a three-stage text chunk rewriting procedure focused on missing reflection, refinement, and completion. These components collectively strengthen the semantic integrity and contextual coherence of chunks. Extensive experiments demonstrate that Meta-Chunking effectively addresses challenges of the chunking task within the RAG system, providing LLMs with more logically coherent text chunks. Additionally, our methodology validates the feasibility of implementing high-quality chunking tasks with smaller-scale models, thereby eliminating the reliance on robust instruction-following capabilities.