Linear probes rely on textual evidence: Results from leakage mitigation studies in language models

This page is a lightweight research summary built from the abstract and metadata while deeper extraction catches up.

Abstract

White-box monitors are a popular technique for detecting potentially harmful behaviours in language models. While they perform well in general, their effectiveness in detecting text-ambiguous behaviour is disputed. In this work, we find evidence that removing textual evidence of a behaviour significantly decreases probe performance. The AUROC reduction ranges from $10$- to $30$-point depending on the setting. We evaluate probe monitors across three setups (Sandbagging, Sycophancy, and Bias), finding that when probes rely on textual evidence of the target behaviour (such as system prompts or CoT reasoning), performance degrades once these tokens are filtered. This filtering procedure is standard practice for output monitor evaluation. As further evidence of this phenomenon, we train Model Organisms which produce outputs without any behaviour verbalisations. We validate that probe performance on Model Organisms is substantially lower than unfiltered evaluations: $0.57$ vs $0.74$ AUROC for Bias, and $0.57$ vs $0.94$ AUROC for Sandbagging. Our findings suggest that linear probes may be brittle in scenarios where they must detect non-surface-level patterns.