用语义不一致指数SINdex检测大模型幻觉，效果优于现有方法。
SINdex: Semantic INconsistency Index for Hallucination Detection in LLMs
- 基于语义嵌入与层次聚类，设计新不一致度量SINdex。
- 在开放与闭卷问答数据集上，最高提升9.3%的检测准确率。
- 无需外部数据，适配主流大模型，适合研究幻觉检测的开发者。
大型语言模型（LLMs）在多个领域广泛应用，但常生成事实错误内容，即“幻觉”。现有缓解策略中，基于不确定性的方法因实现简便、无需外部数据且兼容标准LLM而备受青睐。本文提出一种新颖且可扩展的不确定性驱动语义聚类框架，用于自动化幻觉检测。该方法结合句子嵌入、层次聚类及新提出的不一致度量SINdex，生成更均匀的聚类，提升各类LLM中幻觉检测的准确性。在主流开源与闭源问答数据集上的评估显示，本方法相比最先进技术，最多提升9.3%的AUROC。大量消融实验进一步验证了框架各组件的有效性。
原文摘要 · Abstract (English)
Large language models (LLMs) are increasingly deployed across diverse domains, yet they are prone to generating factually incorrect outputs - commonly known as "hallucinations." Among existing mitigation strategies, uncertainty-based methods are particularly attractive due to their ease of implementation, independence from external data, and compatibility with standard LLMs. In this work, we introduce a novel and scalable uncertainty-based semantic clustering framework for automated hallucination detection. Our approach leverages sentence embeddings and hierarchical clustering alongside a newly proposed inconsistency measure, SINdex, to yield more homogeneous clusters and more accurate detection of hallucination phenomena across various LLMs. Evaluations on prominent open- and closed-book QA datasets demonstrate that our method achieves AUROC improvements of up to 9.3% over state-of-the-art techniques. Extensive ablation studies further validate the effectiveness of each component in our framework.
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。