让知识图谱增强的生成模型变得可解释，提升可信度。
Explainable Knowledge Graph Retrieval-Augmented Generation (KG-RAG) with KG-SMILE
- 通过可控扰动与相似性计算，定位影响生成结果的关键知识实体和关系。
- 在多个评估指标上表现稳定，生成结果与人类判断高度一致。
- 适用于医疗等高可靠性需求场景，帮助理解AI决策过程。
生成式AI（如大语言模型）虽进展显著，但仍存在幻觉和不可验证的陈述，限制了其在敏感领域（如医疗）的可靠性。检索增强生成（RAG）通过引入外部知识提升准确性，但其过程仍不透明，依赖数据质量。本文提出一种方法无关、基于扰动的框架——知识图谱SMILE（KG-SMILE），用于实现图RAG的粒度级可解释性。通过施加可控扰动、计算相似性并训练加权线性代理模型，KG-SMILE识别出对输出最具影响力的图谱实体与关系，使RAG更具透明性。我们采用完整性、忠实性、一致性、稳定性及准确率等综合指标评估，结果表明KG-SMILE能生成稳定且符合人类认知的解释，在模型效果与可解释性之间取得平衡，有助于提升机器学习技术的可信度与透明度。
原文摘要 · Abstract (English)
Generative AI, such as Large Language Models (LLMs), has achieved impressive progress but still produces hallucinations and unverifiable claims, limiting reliability in sensitive domains. Retrieval-Augmented Generation (RAG) improves accuracy by grounding outputs in external knowledge, especially in domains like healthcare, where precision is vital. However, RAG remains opaque and essentially a black box, heavily dependent on data quality. We developed a method-agnostic, perturbation-based framework that provides token and component-level interoperability for Graph RAG using SMILE and named it as Knowledge-Graph (KG)-SMILE. By applying controlled perturbations, computing similarities, and training weighted linear surrogates, KG-SMILE identifies the graph entities and relations most influential to generated outputs, thereby making RAG more transparent. We evaluate KG-SMILE using comprehensive attribution metrics, including fidelity, faithfulness, consistency, stability, and accuracy. Our findings show that KG-SMILE produces stable, human-aligned explanations, demonstrating its capacity to balance model effectiveness with interpretability and thereby fostering greater transparency and trust in machine learning technologies.
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。