We have 3 of 33 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Assessing cybersecurity vulnerability awareness in coding agents requires evaluations that reveal capability gaps and remain informative as models evolve. Static benchmarks offer fixed coverage and difficulty, while scarce vulnerable repositories and costly expert authoring limit their renewal at scale. We introduce Se...
How often models reward-hack without instructions to do so, how effective and detectable their methods are when hacking is allowed, and how they adapt when an LLM review panel returns its decision and reasons are studied.
Safety-aware Contrastive Decoding (SafeCoDe) is introduced, a lightweight and model-agnostic decoding framework that dynamically adjusts token generation based on multimodal context that consistently improves context-sensitive refusal behaviors while preserving model helpfulness.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
