# MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System

arXiv: https://arxiv.org/abs/2503.09600 · HTML: https://mlsanity.com/paper/2503.09600/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 12 Mar 2025.

## Placed in

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

## Builds on (most cited first, 22 of 22)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [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)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023)
- [Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models](https://mlsanity.com/paper/2311.09210/) (2023)
- [A Pretrainer's Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, & Toxicity](https://mlsanity.com/paper/2305.13169/) (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)
- [End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering](https://mlsanity.com/paper/2106.05346/) (2021)
- [WebCPM: Interactive Web Search for Chinese Long-form Question Answering](https://mlsanity.com/paper/2305.06849/) (2023)
- [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)
- [Text Segmentation by Cross Segment Attention](https://mlsanity.com/paper/2004.14535/) (2020)
- [Internal Consistency and Self-Feedback in Large Language Models: A Survey](https://mlsanity.com/paper/2407.14507/) (2024)
- [Is Semantic Chunking Worth the Computational Cost?](https://mlsanity.com/paper/2410.13070/) (2024)
- [Analysing the Robustness of Dual Encoders for Dense Retrieval Against Misspellings](https://mlsanity.com/paper/2205.02303/) (2022)
- [Prompt-Guided Retrieval Augmentation for Non-Knowledge-Intensive Tasks](https://mlsanity.com/paper/2305.17653/) (2023)
- [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)
- [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, 19 of 19)

- [HiChunk: Evaluating and Enhancing Retrieval-Augmented Generation with Hierarchical Chunking](https://mlsanity.com/paper/2509.11552/) (2025)
- [HiKEY: Hierarchical Multimodal Retrieval for Open-Domain Document Question Answering](https://mlsanity.com/paper/2605.29606/) (2026)
- [An Agile Method for Implementing Retrieval Augmented Generation Tools in Industrial SMEs](https://mlsanity.com/paper/2508.21024/) (2025)
- [Knowledge Compression via Question Generation: Enhancing Multihop Document Retrieval without Fine-tuning](https://mlsanity.com/paper/2506.13778/) (2025)
- [MoM: Mixtures of Scenario-Aware Document Memories for Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2510.14252/) (2025)
- [Disco-RAG: Discourse-Aware Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.04377/) (2026)
- [Evaluating Chunking Strategies For Retrieval-Augmented Generation in Oil and Gas Enterprise Documents](https://mlsanity.com/paper/2603.24556/) (2026)
- [Adaptive Chunking: Optimizing Chunking-Method Selection for RAG](https://mlsanity.com/paper/2603.25333/) (2026)
- [Chunking Methods on Retrieval-Augmented Generation - Effectiveness Evaluation Against Computational Cost and Limitations](https://mlsanity.com/paper/2606.00881/) (2026)
- [FreeChunker: A Cross-Granularity Chunking Framework](https://mlsanity.com/paper/2510.20356/) (2025)
- [AgriLens: Semantic Retrieval in Agricultural Texts Using Topic Modeling and Language Models](https://mlsanity.com/paper/2601.08283/) (2026)
- [QChunker: Learning Question-Aware Text Chunking for Domain RAG via Multi-Agent Debate](https://mlsanity.com/paper/2603.11650/) (2026)
- [TopoChunker: Topology-Aware Agentic Document Chunking Framework](https://mlsanity.com/paper/2603.18409/) (2026)
- [M-RAG: Semantic Key-Value Indexing for Retrieval-Augmented Generation](https://mlsanity.com/paper/2603.26667/) (2026)
- [Summarization is Not Dead Yet](https://mlsanity.com/paper/2606.08000/) (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)
- [AutoIndex: Learning Representation Programs for Retrieval](https://mlsanity.com/paper/2607.18603/) (2026)
- [ORDER: Task-Conditioned Routing for Retrieval-Augmented Generation](https://mlsanity.com/paper/2609.17012/) (2026)

## Abstract (arXiv)

Retrieval-Augmented Generation (RAG), while serving as a viable complement to large language models (LLMs), often overlooks the crucial aspect of text chunking within its pipeline. This paper initially introduces a dual-metric evaluation method, comprising Boundary Clarity and Chunk Stickiness, to enable the direct quantification of chunking quality. Leveraging this assessment method, we highlight the inherent limitations of traditional and semantic chunking in handling complex contextual nuances, thereby substantiating the necessity of integrating LLMs into chunking process. To address the inherent trade-off between computational efficiency and chunking precision in LLM-based approaches, we devise the granularity-aware Mixture-of-Chunkers (MoC) framework, which consists of a three-stage processing mechanism. Notably, our objective is to guide the chunker towards generating a structured list of chunking regular expressions, which are subsequently employed to extract chunks from the original text. Extensive experiments demonstrate that both our proposed metrics and the MoC framework effectively settle challenges of the chunking task, revealing the chunking kernel while enhancing the performance of the RAG system.