HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation
This addresses retrieval limitations in RAG systems for applications requiring logical reasoning, though it is incremental as it builds on existing RAG methods.
The paper tackled the problem of imperfect retrieval in Retrieval-Augmented Generation (RAG) systems by proposing HopRAG, a framework that uses graph-structured knowledge exploration and multi-hop reasoning to improve logical relevance, resulting in enhanced answer quality on multi-hop benchmarks.
Retrieval-Augmented Generation (RAG) systems often struggle with imperfect retrieval, as traditional retrievers focus on lexical or semantic similarity rather than logical relevance. To address this, we propose \textbf{HopRAG}, a novel RAG framework that augments retrieval with logical reasoning through graph-structured knowledge exploration. During indexing, HopRAG constructs a passage graph, with text chunks as vertices and logical connections established via LLM-generated pseudo-queries as edges. During retrieval, it employs a \textit{retrieve-reason-prune} mechanism: starting with lexically or semantically similar passages, the system explores multi-hop neighbors guided by pseudo-queries and LLM reasoning to identify truly relevant ones. Experiments on multiple multi-hop benchmarks demonstrate that HopRAG's \textit{retrieve-reason-prune} mechanism can expand the retrieval scope based on logical connections and improve final answer quality.