因果图遇见思维：增强图增强型大语言模型中的复杂推理
Causal Graphs Meet Thoughts: Enhancing Complex Reasoning in Graph-Augmented LLMs
AI总结：
本文提出因果图增强的 Graph RAG 流水线，通过筛选因果边、对齐 CoT 检索并多阶段优化路径，提升 LLM 在医学问答中的复杂推理能力，最高带来 10% 绝对提升。
摘要：
在知识密集型任务中，尤其是在医学和法律等高风险领域，不仅检索相关信息至关重要，提供因果推理和可解释性也同样关键。大语言模型（LLM）已在自然语言理解与生成任务中取得显著性能。然而，它们常受限于难以融合新知识、产生幻觉以及难以解释自身推理过程等问题。为应对这些挑战，将知识图谱与图检索增强生成（Graph RAG）相结合已成为一种有效解决方案。传统 Graph RAG 方法通常依赖简单的图遍历或语义相似度，无法捕捉因果关系，也不能很好地与模型的内部推理步骤对齐。本文提出一种新型流水线，对大型知识图谱进行过滤以突出因果边，使检索过程与模型的思维链（CoT）对齐，并通过多阶段路径改进增强推理。在医学问答任务上的实验显示出稳定增益，在多个大语言模型（LLM）上实现最高 10% 的绝对提升。该方法证明了将因果推理与逐步检索相结合的价值，可为复杂查询带来更具可解释性且逻辑扎实的解决方案。
英文摘要：
In knowledge-intensive tasks, especially in high-stakes domains like medicine and law, it is critical not only to retrieve relevant information but also to provide causal reasoning and explainability. Large language models (LLMs) have achieved remarkable performance in natural language understanding and generation tasks. However, they often suffer from limitations such as difficulty in incorporating new knowledge, generating hallucinations, and explaining their reasoning process. To address these challenges, integrating knowledge graphs with Graph Retrieval-Augmented Generation (Graph RAG) has emerged as an effective solution. Traditional Graph RAG methods often rely on simple graph traversal or semantic similarity, which do not capture causal relationships or align well with the model's internal reasoning steps. This paper proposes a novel pipeline that filters large knowledge graphs to emphasize cause-effect edges, aligns the retrieval process with the model's chain-of-thought (CoT), and enhances reasoning through multi-stage path improvements. Experiments on medical question-answering tasks show consistent gains, with up to a 10\% absolute improvement across multiple large language models (LLMs). This approach demonstrates the value of combining causal reasoning with stepwise retrieval, leading to more interpretable and logically grounded solutions for complex queries.
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。
