2025/01/17 by Zuhong Liu, Liu, Zuhong, Charles-Elie Simon +3 · 1 citation
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Natural Language Processing Techniques #Topic Modeling #Web Data Mining and Analysis
paper · pdf · doi:10.48550/arxiv.2501.09940
openalex publication_date 2025/01/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.