When Protection Overrides Consequences: Understanding Protection Mode in Large Language Model Decision-Making
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
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.
The paper introduces activation probes—directions in a language model’s residual stream—that can both detect and steer safety‑relevant behaviors such as deception, high‑stakes awareness, and sycophancy. By evaluating different estimators (difference‑of‑means vs. logistic regression) and token‑pooling schemes (last, mean, learned attention) on Llama‑3.1‑8B‑Instruct, the authors find that logistic regression excels at detection while difference‑of‑means excels at steering, except for sycophancy where the pattern reverses. The study highlights that the optimal pooling method, layer choice, and steering metric vary by behavior and data, and provides exported probes that enable an interactive interface for scoring and steering text.
arXiv:2606. 15420v1 Announce Type: cross Abstract: A constitution tells a language model what to value, but little tells us whether it does.
arXiv:2607. 10251v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly used in decision support, it is important to understand whether their choices under uncertainty exhibit stable and interpretable behavioural regularities.
arXiv:2611.03374v1 Announce Type: cross Abstract: Recent language model (LM) safety failures have largely been studied as disparate phenomena. In agentic misalignment, a model blackmails an executive...
The paper introduces RiskCueBench, a benchmark designed to separate intent recovery from safety behavior in large language models. It evaluates 25 model groups on 640 prompts covering 160 latent intents across eight risk categories, revealing that higher contextual specificity can reduce refusal rates and safety scores even after intent recovery. The study highlights that safety behavior may be miscalibrated to prompt surface form, underscoring the need for evaluations that condition on semantic recoverability.