探针泛化作为子空间选择：面向OOD欺骗检测
原标题：Probe Generalization as Subspace Selection for OOD Deception Detection
AI 摘要
该研究针对语言模型线性探针在分布外（OOD）数据上泛化失败的问题，提出通过主成分（PC）子空间选择来提升泛化能力。实验基于Llama-3.1-8B-Instruct，在欺骗检测任务上发现，仅使用训练激活分布中少量主成分投影即可实现接近目标分布训练的迁移性能。进一步利用LLM评判器对主成分进行解释和筛选，在Insider Trading Report和Sandbagging数据集上分别缩小了基线到理想性能差距的78%和25%。结果表明，探针的OOD鲁棒性主要由子空间选择决定。
正文节选
Probe Generalization as Subspace Selection for OOD Deception Detection Abstract Linear probes can be used to detect behaviors and concepts inside language model activations, but may fail to transfer to out-of-distribution examples. When studying the generalization performance of Llama-3.1-8B-Instruct probes over 3 held-out deception detection datasets, we find that projecting inputs onto a small subset of principal components (PCs) from the training distribution of activations enables cross-doma