FiDeLiS：大语言模型中用于知识图谱问答的忠实推理
FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answering
AI总结：
提出FiDeLiS框架，利用知识图谱和逐步波束搜索及Path-RAG模块，提升大语言模型在问答中的推理真实性与可解释性，无需训练即可增强性能。
摘要：
大语言模型（LLMs）常常因生成错误或幻觉响应而受到挑战，尤其是在复杂推理任务中。利用知识图谱（KGs）作为外部知识源已成为一种可行的解决方案。然而，现有的知识图谱增强方法，无论是基于检索的还是基于智能体的，在准确检索知识和高效遍历大规模知识图谱方面都面临困难。在本文中，我们提出了一个统一框架FiDeLiS，旨在通过将答案锚定到从知识图谱中检索到的可验证推理步骤来提高LLM响应的真实性。为实现这一目标，我们利用带有演绎评分函数的逐步波束搜索，使LLM能够逐步验证推理过程，并在问题可推导时停止搜索。此外，我们提出了一种Path-RAG模块，为每个波束搜索步骤预选一个较小的候选集，通过缩小搜索空间来降低计算成本。大量实验表明，我们的方法作为一种无需训练的框架，不仅提高了性能，还增强了不同基准上的真实性和可解释性。代码已发布在https://github.com/Y-Sui/FiDeLiS。
英文摘要：
Large Language Models (LLMs) are often challenged by generating erroneous or hallucinated responses, especially in complex reasoning tasks. Leveraging Knowledge Graphs (KGs) as external knowledge sources has emerged as a viable solution. However, existing KG-enhanced methods, either retrieval-based or agent-based, encounter difficulties in accurately retrieving knowledge and efficiently traversing KGs at scale. In this paper, we propose a unified framework, FiDeLiS, designed to improve the factuality of LLM responses by anchoring answers to verifiable reasoning steps retrieved from KGs. To achieve this, we leverage step-wise beam search with a deductive scoring function, allowing the LLM to validate reasoning process step by step, and halt the search once the question is deducible. In addition, we propose a Path-RAG module to pre-select a smaller candidate set for each beam search step, reducing computational costs by narrowing the search space. Extensive experiments show that our method, as a training-free framework, not only improve the performance but also enhance the factuality and interpretability across different benchmarks. Code is released at https://github.com/Y-Sui/FiDeLiS.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
