通过知识图谱 grounding 大语言模型的推理
Grounding LLM Reasoning with Knowledge Graphs
AI总结：
通过知识图谱 grounding 大语言模型的推理，提升推理的准确性和可解释性
摘要：
大型语言模型（LLMs）在生成自然语言答案方面表现出色，但其输出往往难以验证和追溯。知识图谱（KGs）通过结构化的方式表示实体及其关系，为更可靠的推理提供了基础。我们提出了一种新的框架，通过将推理过程的每一步与图结构数据链接，将LLM推理与KGs结合。这种 grounding 将中间的『思考』转化为可解释的轨迹，保持与外部知识的一致性。我们的方法结合了多种推理策略，包括链式思维（CoT）、树状思维（ToT）和图状思维（GoT），并在GRBench上进行评估，该基准用于领域特定的图推理。我们的实验显示了最先进的（SOTA）性能，至少比CoT基线提高了26.5%。除了准确性外，我们还分析了步骤深度、分支结构和模型大小如何影响推理质量，提供了关于支持有效推理条件的见解。这些贡献共同展示了如何通过结构化知识 grounding LLMs，从而在复杂推理任务中实现更高的准确性和更大的可解释性。
英文摘要：
Large Language Models (LLMs) excel at generating natural language answers, yet their outputs often remain unverifiable and difficult to trace. Knowledge Graphs (KGs) offer a complementary strength by representing entities and their relationships in structured form, providing a foundation for more reliable reasoning. We propose a novel framework that integrates LLM reasoning with KGs by linking each step of the reasoning process to graph-structured data. This grounding turns intermediate ``thoughts'' into interpretable traces that remain consistent with external knowledge. Our approach incorporates multiple reasoning strategies, Chain-of-Thought (CoT), Tree-of-Thought (ToT), and Graph-of-Thought (GoT), and is evaluated on GRBench, a benchmark for domain-specific graph reasoning. Our experiments show state-of-the-art (SOTA) performance, with at least 26.5\% improvement over CoT baselines. Beyond accuracy, we analyze how step depth, branching structure, and model size influence reasoning quality, offering insights into the conditions that support effective reasoning. Together, these contributions highlight how grounding LLMs in structured knowledge enables both higher accuracy and greater interpretability in complex reasoning tasks.
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。
