无需外部数据，通过模拟人类判断来检测大模型幻觉。
Zero-source LLM Hallucination Detection with Human-like Criteria Probing
- 用自适应标准分解+加权评分模拟人类评判逻辑。
- 仅靠语义一致性弱监督，实现零源场景下准确检测。
- 结果可解释且性能超越现有方法，适合安全应用。
大型语言模型常生成事实错误或不忠实的内容，威胁其安全使用。在零源条件下（无模型内部信息或外部参考），检测必须仅依赖问答对文本。本文提出人类式标准探查（HCPD）框架，模拟人类多维度推理过程。核心是人类式标准探查（HCP）机制，由一个语言模型代理将判断分解为一组加权的可解释标准，并聚合各标准得分得到最终真实性度量。为实现自适应能力，引入仅依赖语义一致性的奖励对齐方案。推理时采用多采样聚合策略，确保决策稳健性并保持完全可解释性。进一步提供理论分析支持方法可靠性。大量实验表明，HCPD持续优于最先进基线，为零源幻觉检测提供了有效且可解释的解决方案。代码已公开于 https://github.com/TRISKEL10N/HCPD。
原文摘要 · Abstract (English)
Large language models (LLMs) often hallucinate by generating factually incorrect or unfaithful content, posing significant risks to their safe use. Detecting such hallucinations is particularly challenging under the zero-source constraint, where no model internals or external references are available, and detection must rely solely on the textual query-answer pair. In this paper, we propose Human-like Criteria Probing for Hallucination Detection (HCPD), a paradigm that emulates the multi-faceted reasoning of human evaluators. Its core is a Human-like Criteria Probing (HCP) mechanism, in which a LLM agent adaptively decomposes its judgment into a weighted set of interpretable criteria and aggregates criterion-specific scores into a final truthfulness measure. To achieve this adaptive capability, we introduce a reward-based alignment scheme using only weak supervision from semantic consistency. At inference, we employ a multi-sampling aggregation strategy to ensure robust decisions while preserving full interpretability. We further provide theoretical analysis supporting the reliability of our approach. Extensive experiments show that HCPD consistently outperforms state-of-the-art baselines, offering an effective and explainable solution for zero-source hallucination detection. Code is available at https://github.com/TRISKEL10N/HCPD.
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。