AI RESEARCH
ConRAG: Consensus-Driven Multi-View Retrieval for Multi-Hop Question Answering
arXiv CS.CL
•
ArXi:2605.28093v1 Announce Type: new 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.