HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation

2025/02/18 by Hao Liu, Zhengren Wang, Liu, Hao +11 · 6 citations
Computer Science · #Advanced Database Systems and Queries #Algorithms and Data Compression #Computation and Language (cs.CL) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Machine Learning and Algorithms

paper · pdf · doi:10.48550/arxiv.2502.12442

openalex publication_date 2025/02/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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 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 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 retrieve-reason-prune mechanism can expand the retrieval scope based on logical connections and improve final answer quality.

Cited by

• Revisiting Task-Oriented Dataset Search in the Era of Large Language Models: Challenges, Benchmark, and Solution
• Cooperative Retrieval-Augmented Generation for Question Answering: Mutual Information Exchange and Ranking by Contrasting Layers
• Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?
• StepChain GraphRAG: Reasoning Over Knowledge Graphs for Multi-Hop Question Answering
• Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metrics
• Context-Adaptive Synthesis and Compression for Enhanced Retrieval-Augmented Generation in Complex Domains
• Dynamic Context Adaptation for Consistent Role-Playing Agents with Retrieval-Augmented Generations

Related

• You Don't Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures
• PropRAG: Guiding Retrieval with Beam Search over Proposition Paths
• FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs
• MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries
• LevelRAG: Enhancing Retrieval-Augmented Generation with Multi-hop Logic Planning over Rewriting Augmented Searchers