LLM Reasoning with Graphs

LLM: Large Language Model

Ask about this topic

Overview

The field studies how large language models can use graphs to represent relationships, retrieve evidence, and organize multi-step reasoning, especially when answers depend on several connected facts. Common approaches include retrieving paths or subgraphs from knowledge graphs for tasks such as WebQSP and CWQ question answering, giving models tools to navigate graphs, and integrating graph neural networks, symbolic rules, or executable code with language-model reasoning. Other work represents reasoning itself as a chain, tree, or directed graph, and trains models with supervised traces or reinforcement learning to explore paths and verify intermediate steps. These methods can improve multi-hop accuracy and make evidence easier to inspect, but benchmarks also show that graph information is not always used correctly; handling incomplete or noisy evidence, scaling to larger graphs, and demonstrating genuine structural understanding remain open challenges.

Latest papers

CardsList

211 papers28 papers in the last four weeks, up 12% on the four weeks before. 0.2% of all new papers.

Feb 17, 2025

Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answering

Large language models (LLMs) have shown remarkable capabilities in natural language processing. However, in knowledge graph question answering tasks (KGQA), there remains the issue of answering questions that require multi-hop reasoning. Existing methods rely on entity vector matching, but the purpose of the question is abstract and difficult to match with specific entities. As a result, it is difficult to establish reasoning paths to the purpose, which leads to information loss and redundancy. To address this issue, inspired by human reverse thinking, we propose Ontology-Guided Reverse Thinking (ORT), a novel framework that constructs reasoning paths from purposes back to conditions. ORT operates in three key phases: (1) using LLM to extract purpose labels and condition labels, (2) constructing label reasoning paths based on the KG ontology, and (3) using the label reasoning paths to guide knowledge retrieval. Experiments on the WebQSP and CWQ datasets show that ORT achieves state-of-the-art performance and significantly enhances the capability of LLMs for KGQA.

Runxuan Liu, Bei Luo, Jiaqi Li +5

Harbin Institute of Technology, Harbin, China · Beijing University of Posts and Telecommunications, Beijing, China · Joint Laboratory of HIT and iFLYTEK, Beijing, China +2

LLM Reasoning with GraphsGraph-Based RetrievalKnowledge Graph Question AnsweringMulti-Hop Reasoning
AskPDF