HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909622863921152 |
|---|---|
| author | Liu, Hao Wang, Zhengren Chen, Xi Li, Zhiyu Xiong, Feiyu Yu, Qinhan Zhang, Wentao |
| author_facet | Liu, Hao Wang, Zhengren Chen, Xi Li, Zhiyu Xiong, Feiyu Yu, Qinhan Zhang, Wentao |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_12442 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation Liu, Hao Wang, Zhengren Chen, Xi Li, Zhiyu Xiong, Feiyu Yu, Qinhan Zhang, Wentao Information Retrieval Computation and Language 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. |
| title | HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation |
| topic | Information Retrieval Computation and Language |
| url | https://arxiv.org/abs/2502.12442 |