用反向思维构建知识图谱问答路径，提升大模型推理能力
Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answering
- 从问题目标反推条件，构建基于本体的推理路径
- 在WebQSP和CWQ上达到当前最佳性能
- 适合需要多跳推理的知识问答任务
大语言模型在自然语言处理中表现卓越，但在需要多跳推理的知识图谱问答任务中仍存在困难。现有方法依赖实体向量匹配，但问题目标抽象，难以与具体实体对齐，导致推理路径难以建立，信息丢失与冗余严重。受人类反向思维启发，本文提出本体引导的反向思维（ORT）框架，分三阶段进行：（1）使用LLM提取问题目标标签与条件标签；（2）基于知识图谱本体构建标签推理路径；（3）利用该路径指导知识检索。在WebQSP和CWQ数据集上的实验表明，ORT达到当前最优性能，显著提升大模型在知识图谱问答中的能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。