让大模型通过自我反思，更可靠地利用知识图谱回答问题。
Self-Reflective Planning with Knowledge Graphs: Enhancing LLM Reasoning Reliability for Question Answering
- 用知识图谱引导大模型规划推理路径，逐步优化。
- 在三个公开数据集上表现优于现有方法，减少幻觉。
- 适合需要高准确率问答的场景，如医疗、金融领域。
大型语言模型（LLMs）在自然语言处理任务中展现出强大能力，但在缺乏内部知识时容易产生幻觉。尽管将LLMs与知识图谱（KGs）结合可获取结构化、可验证的信息，但现有方法常生成不完整或事实矛盾的推理路径。为此，我们提出自省式规划（SRP）框架，通过迭代的参考引导推理，实现LLMs与KGs的协同。给定问题和主题实体后，SRP首先搜索参考以指导规划与反思；在规划阶段，检查初始关系并生成推理路径；通过推理路径从知识图谱中检索知识后，执行迭代反思，判断检索结果并修正推理路径，直至正确获取答案。在三个公开数据集上的大量实验表明，SRP超越多种强基线模型，进一步验证了其可靠的推理能力。
原文摘要 · Abstract (English)
Recently, large language models (LLMs) have demonstrated remarkable capabilities in natural language processing tasks, yet they remain prone to hallucinations when reasoning with insufficient internal knowledge. While integrating LLMs with knowledge graphs (KGs) provides access to structured, verifiable information, existing approaches often generate incomplete or factually inconsistent reasoning paths. To this end, we propose Self-Reflective Planning (SRP), a framework that synergizes LLMs with KGs through iterative, reference-guided reasoning. Specifically, given a question and topic entities, SRP first searches for references to guide planning and reflection. In the planning process, it checks initial relations and generates a reasoning path. After retrieving knowledge from KGs through a reasoning path, it implements iterative reflection by judging the retrieval result and editing the reasoning path until the answer is correctly retrieved. Extensive experiments on three public datasets demonstrate that SRP surpasses various strong baselines and further underscore its reliable reasoning ability.
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。