Diversify-verify-adapt: Efficient and Robust Retrieval-Augmented Ambiguous Question Answering
This work addresses retrieval-augmented generation for ambiguous queries, offering an incremental improvement over iterative RAG by balancing quality and efficiency.
The paper tackles the problem of low-quality retrieval in ambiguous question answering by proposing the DIVA framework, which diversifies, verifies, and adapts retrieved passages to improve accuracy and robustness while maintaining efficiency.
The retrieval augmented generation (RAG) framework addresses an ambiguity in user queries in QA systems by retrieving passages that cover all plausible interpretations and generating comprehensive responses based on the passages. However, our preliminary studies reveal that a single retrieval process often suffers from low quality results, as the retrieved passages frequently fail to capture all plausible interpretations. Although the iterative RAG approach has been proposed to address this problem, it comes at the cost of significantly reduced efficiency. To address these issues, we propose the diversify-verify-adapt (DIVA) framework. DIVA first diversifies the retrieved passages to encompass diverse interpretations. Subsequently, DIVA verifies the quality of the passages and adapts the most suitable approach tailored to their quality. This approach improves the QA systems accuracy and robustness by handling low quality retrieval issue in ambiguous questions, while enhancing efficiency.