Year: 2025
Type: conference-paper
Abstract: Recent advances in Retrieval-Augmented Generation (RAG) systems have popularized semantic chunking, which aims to improve retrieval performance by dividing documents into semantically coherent segments.Despite its growing adoption, the actual benefits over simpler fixed-size chunking, where documents are split into consecutive, fixed-size segments, remain unclear.This study systematically evaluates the effectiveness of semantic chunking using three common retrieval-related tasks: document retrieval, evidence retrieval, and retrievalbased answer generation.The results show that the computational costs associated with semantic chunking are not justified by consistent performance gains.These findings challenge the previous assumptions about semantic chunking and highlight the need for more efficient chunking strategies in RAG systems.
Authors: Renyi Qu, Ruixuan Tu, Forrest Sheng Bao
Institution: University of Wisconsin–Madison
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4411113004