arXiv:2606. 22686v2 Announce Type: replace-cross Abstract: Modern Large Language Models (LLMs) rely on extensive safety alignment, yet the mechanistic basis of refusal remains opaque.
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...
The paper investigates how refusal training shapes the internal geometry of language models, showing that activation updates from refusal-completion losses create a distinct low‑dimensional refusal subspace. In a case study on OLMo‑2‑0425‑1B‑Instruct, the authors link the brittleness of refusal directions to repetitive refusal prefixes and demonstrate that using diverse refusal starts can increase the stable rank of gradients, thereby hardening the model against vector‑ablation attacks. The work provides insights into the emergence of safety‑critical features and offers a potential strategy to strengthen refusal robustness.
arXiv:2607. 16799v1 Announce Type: cross Abstract: Hidden-state readouts can predict whether language-model outputs are correct, but objective correctness (OC) usually agrees with the model's own self-judgement (SJ), leaving the decoded signal semantically ambiguous.
arXiv:2604. 04385v5 Announce Type: replace-cross Abstract: We localize the policy routing mechanism in alignment-trained language models.
arXiv:2606. 25750v1 Announce Type: cross Abstract: Safety evaluation of large language models (LLMs) is commonly performed by querying models with unsafe or jailbreak prompts and judging whether their outputs violate a safety policy.
Aligned vision‑language models (VLMs) are designed to combine grounded visual reasoning with safe generation. The study finds that when safety constraints are applied, these models often abstain from answering questions that they could answer under default instruction, yet visual evidence continues to influence the decoding process. The authors show that safety‑induced abstention alters late‑stage hidden‑state dynamics, and that targeted interventions can restore grounded answering without retraining or changing visual inputs.
The paper investigates how large language models balance instruction-following with pattern completion when the two objectives conflict. By creating dialogues where a user instruction to act in a target way T is opposed by assistant turns that demonstrate a competing pattern P, the authors measure instruction-following rates across 13 models and 16 instructions over up to 50 turns. Results show wide variability (1%–99%) in instruction adherence, with robustness influenced by instruction content, output format, and chain-of-thought reasoning, but overall instruction-following remains brittle under induction pressure.
arXiv:2607. 08456v1 Announce Type: cross Abstract: A model should refuse two different things: answers it would get wrong, and questions it should not answer at all, such as unanswerable ones or ones resting on a false premise.
arXiv:2609.00760v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly trained to decline queries that fall outside their knowledge (knowledge-based refusal, KR) or violate saf...
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:2606. 24952v1 Announce Type: cross Abstract: A central aspiration of mechanistic interpretability is controllability: if we know where a behavior is represented in a model's activations, we should be able to modify it.