# Passage Segmentation of Documents for Extractive Question Answering

Source: [Passage Segmentation of Documents for Extractive Question Answering](<https://www.sota2.com/research/paper/68fa76961e209131cea6dede>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:12.569Z

Authors: Zuhong Liu, Charles-Elie Simon, Fabien Caspani

Published: 2025-01-17T03:42:18.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2501.09940>)

[PDF](<https://arxiv.org/pdf/2501.09940.pdf>)