arXiv:2605. 26772v1 Announce Type: cross Abstract: Large reasoning models (LRMs) generate chain-of-thought (CoT) traces before producing final outputs, introducing a dynamic internal state that may complicate control mechanisms such as refusal.
arXiv:2603.13359v2 Announce Type: replace Abstract: Language models are commonly fine-tuned for safety alignment to refuse harmful prompts. One approach fine-tunes them to generate categorical refusa...
arXiv:2609.25602v1 Announce Type: new Abstract: In language models, the choice between believing the prompt and believing the weights is made by a handful of identifiable attention heads. Instruction...
arXiv:2609.14759v1 Announce Type: cross Abstract: Alignment applied after pretraining is shallow in a measurable way: a single direction in a model's residual stream can be edited out, and the model...
arXiv:2603.27518v4 Announce Type: replace Abstract: Aligned language models that are trained to refuse harmful requests also exhibit over-refusal: they decline safe instructions that seemingly resemb...
arXiv:2606. 13720v1 Announce Type: new Abstract: Arditi et al.
arXiv:2608.29070v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning traces are increasingly proposed as a mechanism for AI oversight: a monitor inspecting a model's reasoning can, in pri...
The paper introduces PACT, a method for unlearning deceptive behaviors in large language models by using contrastive forget sets that compare a model’s responses under deceptive and neutral contexts. PACT trains the model to produce pressure‑aware counterfactual targets, preserving benign system‑prompt adherence and reasoning traces while dramatically reducing deception rates from over 50% to under 3% on 32B reasoning models.
arXiv:2607. 29062v1 Announce Type: new Abstract: Model capabilities have improved in large part due to scaling chain of thought.
arXiv:2606. 26161v1 Announce Type: new Abstract: Linear directions in activation space have been identified for both refusal and persona traits in instruction-tuned chat models, but the two have been studied as separate mechanisms.
arXiv:2603. 01437v2 Announce Type: replace Abstract: As chain of thought (CoT) has become central to scaling reasoning capabilities in large language models (LLMs), it has also emerged as a promising tool for interpretability, suggesting the opportunity to understand model decisions through verbalized reasoning.
arXiv:2607. 14147v1 Announce Type: cross Abstract: Aligned language models refuse harmful requests, but a one-line prefill ("Sure, here is") strips the refusal.
arXiv:2608. 15772v1 Announce Type: new Abstract: When a language model refuses to answer a prompt, it is unclear whether the correct answer is erased from its internal representations, or merely suppressed at the output layer.