用频域分析隐藏层动态，提升大模型幻觉检测准确率
LLM Hallucination Detection: A Fast Fourier Transform Method Based on Hidden Layer Temporal Signals
- 通过采样多层激活构建时序信号，用FFT提取频域特征
- 在TruthfulQA等数据集上比现有方法提升超10个百分点
- 适合关注推理过程可靠性与模型可信度的研究者
幻觉仍是大语言模型在高可靠性场景部署的关键障碍。现有方法主要分为两类：事实核查受限于外部知识覆盖范围，静态隐藏状态分析无法捕捉推理过程中的动态偏差。为此，我们提出HSAD（基于隐藏信号分析的幻觉检测框架），通过建模自回归生成过程中隐藏表示的时序动态来检测幻觉。该方法在不同层采样激活值构建隐藏层信号，利用快速傅里叶变换（FFT）获得频域表示，并提取最强非直流频率分量作为谱特征。同时，借助大模型的自回归特性，识别出最优观测点以实现高效可靠检测。在多个基准测试中，包括TruthfulQA，HSAD相较现有最先进方法性能提升超过10个百分点。通过融合推理过程建模与频域分析，HSAD为大语言模型的鲁棒幻觉检测建立了新范式。
原文摘要 · Abstract (English)
Hallucination remains a critical barrier for deploying large language models (LLMs) in reliability-sensitive applications. Existing detection methods largely fall into two categories: factuality checking, which is fundamentally constrained by external knowledge coverage, and static hidden-state analysis, that fails to capture deviations in reasoning dynamics. As a result, their effectiveness and robustness remain limited. We propose HSAD (Hidden Signal Analysis-based Detection), a novel hallucination detection framework that models the temporal dynamics of hidden representations during autoregressive generation. HSAD constructs hidden-layer signals by sampling activations across layers, applies Fast Fourier Transform (FFT) to obtain frequency-domain representations, and extracts the strongest non-DC frequency component as spectral features. Furthermore, by leveraging the autoregressive nature of LLMs, HSAD identifies optimal observation points for effective and reliable detection. Across multiple benchmarks, including TruthfulQA, HSAD achieves over 10 percentage points improvement compared to prior state-of-the-art methods. By integrating reasoning-process modeling with frequency-domain analysis, HSAD establishes a new paradigm for robust hallucination detection in LLMs.
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。