MuISQA: Multi-Intent Retrieval-Augmented Generation for Scientific Question Answering

TL;DR

This paper introduces MuISQA, a benchmark and retrieval framework for scientific question answering involving multiple intents, improving evidence coverage and retrieval accuracy over traditional single-intent RAG systems.

Contribution

The paper presents MuISQA, a new benchmark for multi-intent scientific QA and an intent-aware retrieval method leveraging LLMs and RRF for better evidence coverage.

Findings

Outperforms conventional RAG methods in evidence coverage

Achieves higher retrieval accuracy on MuISQA and other datasets

Effectively balances diverse intent coverage with reduced redundancy

Abstract

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.