MuISQA: Multi-Intent Retrieval-Augmented Generation for Scientific Question Answering
By: Zhiyuan Li , Haisheng Yu , Guangchuan Guo and more
Potential Business Impact:
Helps computers answer complex science questions better.
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.
Similar Papers
Biomedical Literature Q&A System Using Retrieval-Augmented Generation (RAG)
Computation and Language
Answers health questions using medical research.
SQuAI: Scientific Question-Answering with Multi-Agent Retrieval-Augmented Generation
Information Retrieval
Answers science questions with proof.
SRAG: Structured Retrieval-Augmented Generation for Multi-Entity Question Answering over Wikipedia Graph
Computation and Language
Helps computers answer questions from many papers.