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. 20479v1 Announce Type: new Abstract: Training probes to detect deceptive outputs from large language models is still an open problem.
arXiv:2602. 01425v2 Announce Type: replace Abstract: Linear probes are a promising approach for monitoring AI systems for deceptive behaviour.
arXiv:2607. 04222v1 Announce Type: new Abstract: Interpretability methods aim to reveal the features represented inside large language models (LLMs).
arXiv:2607. 01208v1 Announce Type: cross Abstract: Language models deployed in high-stakes roles can potentially favor certain entities, brands, or viewpoints, steering user decisions at scale.
arXiv:2602. 14161v2 Announce Type: replace Abstract: Detecting prompt injection, jailbreak attacks, and harmful requests is critical for deploying LLM-based agents safely, yet current evaluation practices in this literature overestimate generalization.
arXiv:2609.00180v1 Announce Type: new Abstract: Large language models sometimes deceive users without being instructed to. However, much of the study on deception in models involves instructed decept...
arXiv:2606. 17478v1 Announce Type: cross Abstract: As LLMs acquire stronger reasoning capabilities, deceptive behavior becomes an increasingly serious safety concern.
The paper introduces a new evaluation setting called scenario‑level out‑of‑distribution (SL‑OOD) detection for SMS and voice phishing, where entire attack scenarios are omitted from training while the label space stays fixed. It shows that high in‑distribution performance does not guarantee robustness to unseen scenarios, attributing this to scenario memorization. The authors propose ECoG, an evidence‑consistent generative framework that uses evidence‑span supervision and a rationale‑label consistency objective, achieving notable improvements in Macro‑F1, reduced prediction‑rationale inconsistency, and higher token‑level overlap with reference evidence.
arXiv:2608. 06417v1 Announce Type: new Abstract: The proliferation of misinformation online has driven demand for scalable detection systems.
arXiv:2608. 02657v1 Announce Type: cross Abstract: Agentic LLMs are vulnerable to indirect prompt injection (IPI) attacks, e.
arXiv:2605. 11554v2 Announce Type: replace Abstract: Task-agnostic structure proxies are often used to interpret why one pretraining corpus transfers better than another, but such explanations require the proxy to track the structure that matters for the downstream task.
The paper identifies a vulnerability in large language models where harmful intent can be hidden within benign narratives, a phenomenon termed Semantic Camouflage. By examining latent activation patterns across several small language model families, the authors discover an "Intent Horizon"—a layer depth where harmful intent representations collapse. They propose Latent Intent Verification (LIV), a lightweight probing defense that detects harmful intent in early layers and outperforms existing guardrails on the PKU-SafeRLHF dataset.