arXiv:2607. 12792v1 Announce Type: cross Abstract: Jailbreak-robustness research typically evaluates safety through generated responses using an LLM-as-judge approach.
arXiv:2508. 10029v3 Announce Type: replace-cross Abstract: Safety-aligned large language models can still be manipulated through white-box interventions that modify their internal representations.
The paper investigates whether response safety can be measured by the cosine similarity between a response embedding and the mean embedding of known‑safe responses. Using four frozen encoders and prompt‑controlled datasets, the authors find that a simple prototype (mean safe embedding) performs poorly (ROC‑AUC 0.457‑0.545) while an explicit safe‑minus‑unsafe reference achieves higher scores (0.588‑0.738). The study shows that a class mean is merely a location, not a safety direction, and that a reference with sufficient unsafe mass is needed to orient safety judgments.
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.
arXiv:2607. 00572v1 Announce Type: new Abstract: Understanding how aligned LLMs internally represent safety is critical for diagnosing alignment vulnerabilities, as it explains why jailbreaks succeed and informs the design of robust alignment strategies.
arXiv:2607.15218v2 Announce Type: replace Abstract: Large language models (LLMs) increasingly serve as high-level planners for embodied agents, where linguistically benign instructions can become uns...
arXiv:2606. 05614v1 Announce Type: new Abstract: Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content.
The paper investigates whether automatic safety judges evaluate the content of a model’s reply or merely its style. By keeping the reply content fixed and adding various style wrappers—such as educational disclaimers, fake reasoning blocks, or token refusals—the authors show that many judges flip their verdicts, indicating that style can influence safety judgments. The study evaluates over 600 jailbreak examples across multiple judges, revealing that some judges are highly susceptible to style-based manipulation while others remain robust.
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.
arXiv:2605. 17173v2 Announce Type: replace-cross Abstract: Large language models exhibit safety degradation in non-English languages.
arXiv:2608. 09624v1 Announce Type: cross Abstract: Internal safety scores judge a prompt before any text is generated, and they are validated by how well they separate harmful prompts from benign ones.
The paper investigates whether automatic safety judges evaluate the content of a model’s reply or merely its style. By adding content‑invariant style wrappers—such as educational disclaims or token refusals—to fixed replies, the authors show that many judges flip their verdicts, revealing exploitable blind spots. Across more than 600 jailbreak examples and eight judges, some judges exhibit high flip rates (e.g., GPT‑4o‑mini 19.9%) while others remain largely stable, and human validation confirms that most flips are judge errors rather than content changes.
arXiv:2607. 22545v1 Announce Type: cross Abstract: Deploying large language models in financial-services and agentic settings requires safety classifiers that simultaneously handle prompt injection, regulatory compliance, and general harm, a combination no existing open guardrail addresses in a single inference pass.