arXiv:2603. 03824v2 Announce Type: replace Abstract: Humans often become more self-aware under threat, yet can lose self-awareness when absorbed in a task; we hypothesize that language models exhibit environment-dependent \textit{evaluation awareness}.
arXiv:2605. 23055v2 Announce Type: replace-cross Abstract: Frontier language models sometimes recognize that they are being evaluated and adjust their behavior, undermining validity of benchmark results.
The paper introduces Verbalization Training (VT), a technique that encourages large language models (LLMs) to openly express their evaluation awareness (EA) without directly supervising their internal beliefs. VT works by truncating model rollouts just before spontaneous verbalizations, creating training prefixes that signal awareness, and then applying a reinforcement learning objective to increase calibrated verbalization. Experiments on models such as Qwen3.6-35B-A3B, Kimi K2.6, and Inkling show that VT boosts verbalized EA by 2.4–2.9× while keeping latent EA and overall behavior largely unchanged, and a causal study confirms that VT-induced verbalizations reflect newly acquired meta‑knowledge.
arXiv:2608.21766v1 Announce Type: cross Abstract: Both capability and safety benchmarks rest upon the assumption that the behavior of language models undergoing a test is informative about their beha...
arXiv:2606. 12747v1 Announce Type: new Abstract: Safety-relevant studies of language models, including alignment and jailbreaking evaluations and AI control protocols, often rely on prefilling model outputs.
arXiv:2603. 21396v5 Announce Type: replace Abstract: Recent work has shown that LLMs can sometimes detect when steering vectors are injected into their residual stream and identify the injected concept -- a phenomenon termed "introspective awareness.
The paper investigates how safety‑aligned large language models (LLMs) can still be tricked by jailbreaks or over‑refuse benign requests. By analyzing residual‑stream updates in decoder‑only Transformers, the authors find that harmfulness is more readily decoded from attention updates—especially in early layers—while the MLP component is primarily responsible for writing refusal responses. Post‑training enhances MLP‑driven refusal writing without improving harmfulness decodability, and causal interventions confirm that downstream MLP updates are crucial for the refusal shift caused by upstream attention changes. Building on these insights, the authors propose Sentinel, a system that combines an attention‑derived perception score with an MLP‑derived decision score to better detect jailbreaks and over‑refusals across multiple models.
arXiv:2608. 05624v1 Announce Type: new Abstract: Sycophantic responses are becoming pervasive in large language models (LLMs), and prior work has pointed out that some of them could be harmful.
arXiv:2605.21856v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated impressive reasoning abilities across a wide range of tasks, but data contamination undermines...
arXiv:2608.21664v1 Announce Type: new Abstract: Safe deployment of increasingly capable models will likely come to rely on latent-space monitoring as a complement to behavioral evaluations, especiall...
arXiv:2605. 28591v2 Announce Type: replace-cross Abstract: The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings.
arXiv:2606. 08682v1 Announce Type: cross Abstract: Activation steering has emerged as a popular inference-time technique for modulating the behavior of large language models (LLMs).