# Passage Segmentation of Documents for Extractive Question Answering

arXiv: https://arxiv.org/abs/2501.09940 · HTML: https://mlsanity.com/paper/2501.09940/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 17 of its 20 references that are in the map.
- First posted on arXiv 17 Jan 2025.

## Placed in

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

## Builds on (most cited first, 17 of 17)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [The NarrativeQA Reading Comprehension Challenge](https://mlsanity.com/paper/1712.07040/) (2017)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [Ragas: Automated Evaluation of Retrieval Augmented Generation](https://mlsanity.com/paper/2309.15217/) (2023)
- [Improving Text Embeddings with Large Language Models](https://mlsanity.com/paper/2401.00368/) (2023)
- [RAFT: Adapting Language Model to Domain Specific RAG](https://mlsanity.com/paper/2403.10131/) (2024)
- [Dense X Retrieval: What Retrieval Granularity Should We Use?](https://mlsanity.com/paper/2312.06648/) (2023)
- [Learning to Filter Context for Retrieval-Augmented Generation](https://mlsanity.com/paper/2311.08377/) (2023)
- [Lynx: An Open Source Hallucination Evaluation Model](https://mlsanity.com/paper/2407.08488/) (2024)
- [LumberChunker: Long-Form Narrative Document Segmentation](https://mlsanity.com/paper/2406.17526/) (2024)
- [Grounding Language Model with Chunking-Free In-Context Retrieval](https://mlsanity.com/paper/2402.09760/) (2024)

## Built on by (most cited first, 6 of 6)

- [LightMem: Lightweight and Efficient Memory-Augmented Generation](https://mlsanity.com/paper/2510.18866/) (2025)
- [UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities](https://mlsanity.com/paper/2504.20734/) (2025)
- [A Systematic Investigation of Document Chunking Strategies and Embedding Sensitivity](https://mlsanity.com/paper/2603.06976/) (2026)
- [RAGTurk: Best Practices for Retrieval Augmented Generation in Turkish](https://mlsanity.com/paper/2602.03652/) (2026)
- [TextBite: A Historical Czech Document Dataset for Logical Page Segmentation](https://mlsanity.com/paper/2503.16664/) (2025)
- [SegNSP: Revisiting Next Sentence Prediction for Linear Text Segmentation](https://mlsanity.com/paper/2601.03474/) (2026)

## Abstract (arXiv)

Retrieval-Augmented Generation (RAG) has proven effective in open-domain question answering. However, the chunking process, which is essential to this pipeline, often receives insufficient attention relative to retrieval and synthesis components. This study emphasizes the critical role of chunking in improving the performance of both dense passage retrieval and the end-to-end RAG pipeline. We then introduce the Logits-Guided Multi-Granular Chunker (LGMGC), a novel framework that splits long documents into contextualized, self-contained chunks of varied granularity. Our experimental results, evaluated on two benchmark datasets, demonstrate that LGMGC not only improves the retrieval step but also outperforms existing chunking methods when integrated into a RAG pipeline.