Search papers, labs, and topics across Lattice.
The paper introduces QChunker, a novel approach to text chunking for RAG that restructures the paradigm to understanding-retrieval-augmentation. It uses a multi-agent debate framework with specialized components for question outline generation, text segmentation, integrity review, and knowledge completion, inspired by the idea that questions drive insights. The authors also introduce ChunkScore, a direct evaluation metric for chunk quality, and demonstrate QChunker's effectiveness across diverse domains, improving RAG performance by providing more coherent and informative text chunks.
Forget brittle retrieval: QChunker uses a question-aware multi-agent debate to restructure RAG from retrieval-augmentation to *understanding*-retrieval-augmentation, boosting performance across diverse domains.
The effectiveness upper bound of retrieval-augmented generation (RAG) is fundamentally constrained by the semantic integrity and information granularity of text chunks in its knowledge base. To address these challenges, this paper proposes QChunker, which restructures the RAG paradigm from retrieval-augmentation to understanding-retrieval-augmentation. Firstly, QChunker models the text chunking as a composite task of text segmentation and knowledge completion to ensure the logical coherence and integrity of text chunks. Drawing inspiration from Hal Gregersen's"Questions Are the Answer"theory, we design a multi-agent debate framework comprising four specialized components: a question outline generator, text segmenter, integrity reviewer, and knowledge completer. This framework operates on the principle that questions serve as catalysts for profound insights. Through this pipeline, we successfully construct a high-quality dataset of 45K entries and transfer this capability to small language models. Additionally, to handle long evaluation chains and low efficiency in existing chunking evaluation methods, which overly rely on downstream QA tasks, we introduce a novel direct evaluation metric, ChunkScore. Both theoretical and experimental validations demonstrate that ChunkScore can directly and efficiently discriminate the quality of text chunks. Furthermore, during the text segmentation phase, we utilize document outlines for multi-path sampling to generate multiple candidate chunks and select the optimal solution employing ChunkScore. Extensive experimental results across four heterogeneous domains exhibit that QChunker effectively resolves aforementioned issues by providing RAG with more logically coherent and information-rich text chunks.
Tsinghua AI