现有幻觉检测方法在分布外场景下失效，仅依赖数据相关性而非真实推理能力。
Representation-based Broad Hallucination Detectors Fail to Generalize Out of Distribution
- 通过控制数据相关性，发现顶级模型性能仅相当于简单线性探测器。
- 所有方法在分布外测试中表现接近随机，泛化能力极差。
- 提出评估幻觉检测的新指南，强调需避免虚假相关性干扰。
我们评估了当前最先进的幻觉检测方法的有效性，发现其在RAGTruth数据集上的表现主要由数据中的虚假相关性驱动。在控制该因素后，现有最先进方法的表现并不优于监督线性探测器，且需要在不同数据集上进行大量超参数调优。分布外泛化目前仍无法实现，所有分析的方法在新数据上表现均接近随机。为此，我们提出一套幻觉检测及其评估的指导原则。
原文摘要 · Abstract (English)
We critically assess the efficacy of the current SOTA in hallucination detection and find that its performance on the RAGTruth dataset is largely driven by a spurious correlation with data. Controlling for this effect, state-of-the-art performs no better than supervised linear probes, while requiring extensive hyperparameter tuning across datasets. Out-of-distribution generalization is currently out of reach, with all of the analyzed methods performing close to random. We propose a set of guidelines for hallucination detection and its evaluation.
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。