arXiv:2607. 20479v1 Announce Type: new Abstract: Training probes to detect deceptive outputs from large language models is still an open problem.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2606. 17478v1 Announce Type: cross Abstract: As LLMs acquire stronger reasoning capabilities, deceptive behavior becomes an increasingly serious safety concern.
Linear probes can identify behaviors in language model activations but often fail on out‑of‑distribution data. This study shows that projecting inputs onto a small set of principal components (PCs) from the training distribution allows probes for Llama‑3.1‑8B‑Instruct to transfer across three deception‑detection datasets, nearly matching probes trained directly on the test data. By scoring PCs with an LLM judge to select those that encode transferable deception directions, the authors close the baseline‑to‑oracle gap by 78% on Insider Trading Report and 25% on Sandbagging, revealing that subspace selection largely determines OOD robustness.
arXiv:2607. 20444v1 Announce Type: cross Abstract: Large language models (LLMs) can produce deceptive responses: outputs that mislead users in service of a contextually or experimentally induced goal.
arXiv:2602. 01425v2 Announce Type: replace Abstract: Linear probes are a promising approach for monitoring AI systems for deceptive behaviour.
arXiv:2607. 01567v1 Announce Type: new Abstract: Deceptive behavior in LLMs is costly to monitor and prevent, motivating approaches such as Scalable Oversight via Lie Detectors (SOLiD) (Cundy & Gleave, 2025), which uses lie detectors to identify responses for review by high-cost labelers.
The paper examines the reliability of lie detection probes for language models when the models adopt anti-factual personas, such as conspiracy theorists. A dataset of 8,916 human-reviewed responses from three LLMs was created, and eight existing probes were evaluated, revealing many fail to flag falsehoods under these personas. The authors also constructed confounder datasets showing that probes often track spurious correlations like instruction compliance, and propose a simple linear probe that performs best on both persona and confounder tests.