Reliable Reasoning Path: Distilling Effective Guidance for LLM Reasoning With Knowledge Graphs
Top Cited Papers
- 22 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (4) , 2380-2393
Abstract
Large language models (LLMs) often struggle with knowledge-intensive tasks due to a lack of background knowledge and a tendency to hallucinate. To address these limitations, integrating knowledge graphs (KGs) with LLMs has been intensively studied. Existing KG-enhanced LLMs focus on supplementary factual knowledge, but still struggle with solving complex questions. We argue that refining the relationships among facts and organizing them into a logically consistent reasoning path is equally important as factual knowledge itself. Despite their potential, extracting reliable reasoning paths from KGs poses the following challenges: the complexity of graph structures and the existence of multiple generated paths, making it difficult to distinguish between useful and redundant ones. To tackle these challenges, we propose the RRP framework to mine the knowledge graph, which combines the semantic strengths of LLMs with structural information obtained through relation embedding and bidirectional distribution learning. Additionally, we introduce a rethinking module that evaluates and refines reasoning paths according to their significance. Experimental results on two public datasets show that RRP achieves state-of-the-art performance compared to existing baseline methods. Moreover, RRP can be easily integrated into various LLMs to enhance their reasoning abilities in a plug-and-play manner. By generating high-quality reasoning paths tailored to specific questions, RRP distills effective guidance for LLM reasoning.Keywords
All Related Versions
Funding Information
- Innovation and Technology Commission of the Hong Kong Special Administrative Region (ITS/263/24FP)
This publication has 10 references indexed in Scilit:
- Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning2025
- LightRAG: Simple and Fast Retrieval-Augmented Generation2025
- Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs2024
- Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?2024
- Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning2024
- QALD-9-plus: A Multilingual Dataset for Question Answering over DBpedia and Wikidata Translated by Native Speakers2022
- Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals2021
- K-BERT: Enabling Language Representation with Knowledge GraphProceedings of the AAAI Conference on Artificial Intelligence, 2020
- Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings2020
- Glove: Global Vectors for Word Representation2014