MuISQA: Multi-Intent Retrieval-Augmented Generation for Scientific Question Answering
This addresses the limitation of single-intent RAG systems for complex scientific question answering, though it is incremental as it builds on existing RAG methods with a novel decomposition approach.
The paper tackles the problem of incomplete evidence coverage in retrieval-augmented generation (RAG) systems for multi-intent scientific questions by introducing the MuISQA benchmark and an intent-aware retrieval framework, which outperforms conventional approaches in retrieval accuracy and evidence coverage.
Complex scientific questions often entail multiple intents, such as identifying gene mutations and linking them to related diseases. These tasks require evidence from diverse sources and multi-hop reasoning, while conventional retrieval-augmented generation (RAG) systems are usually single-intent oriented, leading to incomplete evidence coverage. To assess this limitation, we introduce the Multi-Intent Scientific Question Answering (MuISQA) benchmark, which is designed to evaluate RAG systems on heterogeneous evidence coverage across sub-questions. In addition, we propose an intent-aware retrieval framework that leverages large language models (LLMs) to hypothesize potential answers, decompose them into intent-specific queries, and retrieve supporting passages for each underlying intent. The retrieved fragments are then aggregated and re-ranked via Reciprocal Rank Fusion (RRF) to balance coverage across diverse intents while reducing redundancy. Experiments on both MuISQA benchmark and other general RAG datasets demonstrate that our method consistently outperforms conventional approaches, particularly in retrieval accuracy and evidence coverage.