用知识图谱对比法检测并解释大模型幻觉，提升可信度。
KEA Explain: Explanations of Hallucinations using Graph Kernel Analysis
- 构建模型输出与真实数据的知识图谱，用图核比对差异
- 在开放与封闭领域任务中均实现良好幻觉检测准确率
- 可生成对比性解释，适合高风险场景的可信AI研究
大语言模型常产生看似合理但无事实依据的幻觉。本文提出KEA（Kernel-Enriched AI） Explain：一种神经符号框架，通过比较模型输出构建的知识图谱与维基数据（Wikidata）或上下文文档中的真实知识，检测并解释幻觉。利用图核与语义聚类技术，该方法能提供可解释的幻觉成因分析，兼具鲁棒性与透明性。实验表明，框架在开放域与封闭域任务中均具备竞争力的检测性能，并支持生成对比性解释，增强系统可解释性。本研究提升了大模型在高风险场景下的可靠性，为未来精度优化与多源知识融合奠定基础。
原文摘要 · Abstract (English)
Large Language Models (LLMs) frequently generate hallucinations: statements that are syntactically plausible but lack factual grounding. This research presents KEA (Kernel-Enriched AI) Explain: a neurosymbolic framework that detects and explains such hallucinations by comparing knowledge graphs constructed from LLM outputs with ground truth data from Wikidata or contextual documents. Using graph kernels and semantic clustering, the method provides explanations for detected hallucinations, ensuring both robustness and interpretability. Our framework achieves competitive accuracy in detecting hallucinations across both open- and closed-domain tasks, and is able to generate contrastive explanations, enhancing transparency. This research advances the reliability of LLMs in high-stakes domains and provides a foundation for future work on precision improvements and multi-source knowledge integration.
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。