让AI生成时能识别因果关系，避免误把相关当因果。
CDF-RAG: Causal Dynamic Feedback for Adaptive Retrieval-Augmented Generation
- 用动态反馈迭代优化检索，寻找因果图谱
- 在四个数据集上准确率和因果正确性显著提升
- 适合需要逻辑严谨性的科研与决策类应用
检索增强生成（RAG）通过引入外部知识检索，显著提升了大语言模型在知识密集型任务中的表现。然而，现有RAG框架主要依赖语义相似性和相关性驱动的检索，难以区分真实因果关系与虚假关联，导致生成结果虽事实正确但缺乏因果机制解释，造成信息不完整或误导。为此，我们提出因果动态反馈的自适应检索增强生成框架（CDF-RAG），旨在提升生成推理的因果一致性、事实准确性和可解释性。CDF-RAG通过迭代优化查询、检索结构化因果图，并支持跨知识源的多跳因果推理。同时，它通过因果路径验证回答，确保输出逻辑连贯且事实可靠。我们在四个不同数据集上评估了CDF-RAG，结果表明其在响应准确性和因果正确性方面优于现有RAG方法。代码已公开于https://github.com/elakhatibi/CDF-RAG。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) has significantly enhanced large language models (LLMs) in knowledge-intensive tasks by incorporating external knowledge retrieval. However, existing RAG frameworks primarily rely on semantic similarity and correlation-driven retrieval, limiting their ability to distinguish true causal relationships from spurious associations. This results in responses that may be factually grounded but fail to establish cause-and-effect mechanisms, leading to incomplete or misleading insights. To address this issue, we introduce Causal Dynamic Feedback for Adaptive Retrieval-Augmented Generation (CDF-RAG), a framework designed to improve causal consistency, factual accuracy, and explainability in generative reasoning. CDF-RAG iteratively refines queries, retrieves structured causal graphs, and enables multi-hop causal reasoning across interconnected knowledge sources. Additionally, it validates responses against causal pathways, ensuring logically coherent and factually grounded outputs. We evaluate CDF-RAG on four diverse datasets, demonstrating its ability to improve response accuracy and causal correctness over existing RAG-based methods. Our code is publicly available at https://github.com/ elakhatibi/CDF-RAG.
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。