The paper investigates how fine‑tuning large language models with a small number of harmful examples can erode their refusal behavior, and explores whether localizing safety‑related behavior to specific layers or directions can provide robust defenses. Experiments across six checkpoints from four model families show that harmful and benign prompts remain linearly separable after attack, and that patching clean hidden states or freezing layers up to a transition depth can restore refusal. However, attackers can bypass these defenses by spreading updates or targeting singular directions, indicating that adaptive fine‑tuning can defeat localized repairs and highlighting the need for multiple defensive checks.
By Jungseob Lee, Dongyub Jude Lee, Sugyeong Eo, Seongtae Hong, Seungyoon Lee, Heuiseok Lim
arXiv:2608. 08542v1 Announce Type: new Abstract: Model merging has become the default way to give an aligned language model new skills without retraining: a practitioner folds task vectors from math, code, or domain specialists into a safety-aligned base using task arithmetic, TIES, or DARE.
By Yu Ma, Hongli Shi, Jing Li, Xinran Xu, Weiwei Hou
arXiv:2607. 25063v1 Announce Type: new Abstract: Developers judge a model checkpoint by how it behaves.
By Cen Lu, Yung-Chen Tang, Andrea Cavallaro
arXiv:2607. 01239v1 Announce Type: cross Abstract: Character-level perturbations bypass safety alignment in modern LLMs despite leaving prompts human-readable.
By Tung-Ling Li, Hongliang Liu, Yuhao Wu
The paper introduces ‘Fool’s Gold’, a defensive deception technique for open‑weight language models that hardens them against safety‑removal attacks. By training decoy responses within a differentiable simulation of the attack, the method poisons the payoff of stripped refusal mechanisms, producing confident but falsified answers to hazardous requests while preserving benign behavior. Experiments on seven models (9B‑122B) show that 51‑90% of attacked‑state responses become decoys, with the defense accounting for 27‑84% of this effect, and that the defended 122B model remains within benign‑behavior budgets.
By Mark Russinovich
arXiv:2607. 14147v1 Announce Type: cross Abstract: Aligned language models refuse harmful requests, but a one-line prefill ("Sure, here is") strips the refusal.
By Alex Kwon
arXiv:2607. 27281v1 Announce Type: new Abstract: A capability appears in a language model when the last parts of its circuit align in one stochastic attempt, and getting all but one right is worth nothing.
By Lei Dong
arXiv:2605.14605v3 Announce Type: replace-cross
Abstract: Model providers increasingly release the weights of large language models. Although these models are safety-aligned before release, their saf...
By Itay Zloczower, Eyal Lenga, Gilad Gressel, Yisroel Mirsky
The paper introduces ADVERSA, an automated red‑teaming framework that evaluates large language model safety over multiple turns by tracking continuous compliance trajectories instead of binary jailbreak outcomes. Using a fine‑tuned 70B attacker model and a structured 5‑point rubric, the authors conduct controlled experiments on three frontier victim models, measuring guardrail degradation and judge reliability through a triple‑judge consensus. Results show a 26.7% jailbreak rate with most breaches occurring early, and the study documents inter‑judge agreement, attacker drift, and attacker refusals as key factors affecting safety assessment.
By Harry Owiredu-Ashley
The paper introduces SafeStart, a technique for Mixture-of-Experts (MoE) language models that mitigates the safety degradation caused by active expert reduction during serving. By running all experts for the prompt and the first eight generated tokens before switching to a reduced set, SafeStart largely restores the model’s refusal to harmful requests while preserving most of the speedup achieved by expert reduction. Experiments on several MoE models show that SafeStart maintains high offline decode speedups (≈85% of the original) and limits the increase in harmful responses to within a few percentage points, even under jailbreak prompts.
By Erfan Baghaei Potraghloo, Saeid Shokoufa, Seyedarmin Azizi, Arya Fayyazi, Souvik Kundu, Mehdi Kamal, Massoud Pedram
The paper investigates where the ‘refusal’ behavior of language models resides across different architectures. It finds that a single direction in the residual stream governs refusal in transformers, and that the same direction—after a rigid rotation—also governs refusal in state‑space models (SSMs). By aligning these directions and applying a detector‑triggered gate, the authors demonstrate that refusal can be effectively transferred across transformer, SSM, recurrent, and hybrid architectures, showing that safety tooling can be ported by re‑estimating the direction at each architecture’s write site rather than rebuilding it from scratch.
By Preethi Carmel Bosco, Gopalakrishnan Srinivasan
arXiv:2610.15218v1 Announce Type: new
Abstract: A recurrent-depth language model reuses one block of weights several times in a row. The number of repetitions, which we call loops, is chosen when the...
By Seyedarmin Azizi, Erfan Baghaei Potraghloo, Arya Fayyazi, Saeid Shokoufa, Massoud Pedram