We have 4 of 18 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.
Large language models frequently fail to balance staying truthful with being supportive. They often exhibit sycophancy in responses to users, agreeing with false claims, offering unwarranted flattery, and giving advice skewed toward users'expressed views. In reality, sycophancy rarely happens in a single exchange; it m...
The framework and EvalAwareBench provide the tools to measure, attribute, and mitigate evaluation awareness, building the foundation for future solutions to ground evaluation awareness in social psychology.
Evaluation awareness (EA) can cause large language models (LLMs) to behave differently during audits than in deployment, yet measuring and accounting for EA remains challenging. We introduce verbalization training (VT), a method for making LLMs less reticent about verbalizing evaluation awareness while avoiding to supe...
This work introduces SEABench, a benchmark for studying endogenous misalignment arising from agent self-evolution, with 48 longitudinal task sequences that span multiple evolution surfaces, task domains, and harm types in a rich personal-assistant environment and shows that qualitatively different safety behaviors emer...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
