arXiv:2607. 17427v1 Announce Type: new Abstract: Abliteration - deleting a model's refusal direction from its weights - is the standard recipe behind popular "uncensored" open-weight models.
arXiv:2608. 13063v1 Announce Type: new Abstract: Prior work on LLM behavior under anomalous conditions asks whether a model notices anomalies.
arXiv:2606. 05183v2 Announce Type: replace-cross Abstract: Pass/fail safety evaluation reports whether a model refused.
arXiv:2608. 17202v1 Announce Type: new Abstract: Safety alignment in open-weight language models is trivially removable: abliteration projects a refusal-mediating direction out of the weights in minutes, and no release-time defense we are aware of prevents it durably.
arXiv:2608. 12599v1 Announce Type: new Abstract: Multi-turn dialogues let users revoke constraints as easily as impose them, but revocation does not reliably take effect: models keep enacting withdrawn requirements (occasionally beneath comments asserting their removal), a failure we call \emph{behavioral relapse}, or revocation inertia.
arXiv:2607. 12200v1 Announce Type: new Abstract: As frontier language models advance, policymakers and model developers need methods for assessing whether model access materially increases a non-expert actor's ability to plan high-consequence Chemical, Biological, Radiological, or Nuclear (CBRN) misuse relative to public tools alone.
arXiv:2608. 15286v1 Announce Type: cross Abstract: We introduce AgentRelBench, an environment-agnostic reliability instrument that computes ground-truth, severity-priced damage from database state diffs across repeated runs, with no LLM in the measurement path, demonstrated on EnterpriseOps-Gym.
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:2606. 07834v1 Announce Type: cross Abstract: LLM judges increasingly turn verdicts into system commitments.
arXiv:2608. 11822v1 Announce Type: cross Abstract: A growing body of work reports that language models represent task-relevant latent structure that they fail to use.
arXiv:2607. 28639v1 Announce Type: cross Abstract: We show that knowledge distillation in small instruction-tuned language models has asymmetric effects on bias.
arXiv:2607. 23976v1 Announce Type: cross Abstract: Appending a two-word confirmation tag to a decision question -- "Is X the better choice?
arXiv:2608. 03842v1 Announce Type: cross Abstract: When a language model fails on surface-perturbed input (typos, OCR noise, homophones), "which layer is responsible" has three natural operationalizations: where representations diverge most (sensitivity), where restoring clean activations recovers the prediction (causality), and where a small adapter can repair the damage (compensatory capacity) - and we show these three layer maps dissociate.