arXiv AI
Jun 15
Refusal Beyond a Single Direction: A Preliminary Comparison of Diff-in-Means and INLP
arXiv:2606. 13720v1 Announce Type: new Abstract: Arditi et al.
Beyond a Single Direction: Chain-of-Thought Disrupts Simple Steering of Refusal
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.
Related stories
arXiv AI
Aug 3
On the Generalization of Steering Vectors for Chain-of-Thought Faithfulness
arXiv:2607. 29062v1 Announce Type: new Abstract: Model capabilities have improved in large part due to scaling chain of thought.
arXiv AI
Jun 26
Refusal Lives Downstream of Persona in Chat Models
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 AI
Jul 24
Post-Hoc Reasoning in Chain of Thought: Decoding and Steering Pre-Committed Answers
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 AI
Jul 17
Breaking Refusal in the First Half: A Mechanistic Study of the Prefill Jailbreak
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 AI
1d ago
Broken Symmetry in LLM Refusal: Answer Release Is More Local Than Refusal Restoration
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.
arXiv AI
Jun 26
Where Do CoT Training Gains Land in LLM based Agents?
arXiv:2606. 26935v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning is widely used in language-model agents, but prior work has shown that verbalized CoT is not always faithful and may instead reflect post-hoc reasoning, which means the model already knows the answer before reasoning.
arXiv AI
Jun 8
Endogenous Resistance to Activation Steering in Language Models
arXiv:2602. 06941v2 Announce Type: replace-cross Abstract: Large language models can recover mid-generation from task-misaligned activation steering, producing explicit verbal restarts (e.
arXiv AI
Jun 8
Latent-space Attacks for Refusal Evasion in Language Models
arXiv:2605. 21706v2 Announce Type: replace Abstract: Safety-aligned language models are trained to refuse harmful requests, yet refusal behavior can be suppressed by steering their internal representations.
arXiv AI
Jun 26
Humans Disengage, Reasoning Models Persist: Separating Difficulty Registration from Deliberation Allocation
arXiv:2606. 26502v1 Announce Type: new Abstract: Large reasoning models (LRMs) take longer on harder problems, just as humans do.
arXiv AI
Aug 10
Divergent Response Modes in Frontier Language Models Under Steering Pressure
arXiv:2608. 06578v1 Announce Type: new Abstract: Frontier language models are trained using distinct data, objectives, and safety pipelines.
arXiv AI
Aug 10
Counterfactual Simulation Training for Chain-of-Thought Faithfulness
arXiv:2602. 20710v2 Announce Type: replace Abstract: Inspecting Chain-of-Thought reasoning is among the most common means of understanding why an LLM produced its output.