ConRAG: Consensus-Driven Multi-View Retrieval for Multi-Hop Question Answering
For researchers and practitioners in multi-hop QA, ConRAG provides a more effective retrieval method that significantly improves LLM performance on complex reasoning tasks.
ConRAG introduces a consensus-driven multi-view RAG framework that optimizes both query and corpus sides using relation, entity, and text signals, achieving up to +26.9% average gains over vanilla RAG and a new SOTA on MuSiQue with Gemma-4-31B.
Retrieval-augmented generation (RAG) has emerged as a promising paradigm for enhancing large language models (LLMs) on multi-hop question answering (QA), which requires reasoning over evidence from multiple documents. Current multi-hop RAG methods generally focus on either query-side task decomposition or corpus-side knowledge graph construction. Despite their progress, these methods still struggle to achieve satisfactory performance on complex multi-hop QA tasks. To this end, we propose ConRAG, a consensus-driven multi-view RAG framework that effectively boosts LLMs on complex multi-hop QA. The core of ConRAG is to systematically optimize both the query and corpus sides and to leverage multi-view evidence (relation, entity, and text signals) for more accurate retrieval. Extensive experiments on three multi-hop QA benchmarks show that ConRAG consistently outperforms all baselines by a clear margin, e.g., up to +26.9% average performance gains over vanilla RAG, and enables Gemma-4-31B to achieve a new state-of-the-art record on the challenging MuSiQue benchmark.