We have 3 of 4 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.
LLM evaluation pipelines often have many candidate judges: general LLM-as-a-judge prompts, reward models, safety classifiers, confidence variants, and task-specific verifiers. The deployment question is not only which judge is best, but which judges should be called, on which examples, and when panel construction shoul...
Prefix-Normalized Policy Optimization (PNPO), which replaces the cumulative ratio with the geometric mean of likelihood ratios along each causal prefix, preserving causal-prefix dependence at each position while compressing the log-weight scale, is studied.
Language models suffer from adversarial vulnerability, where imperceptible perturbations in inputs can mislead model predictions. Existing adversarial training methods enhance model robustness by augmenting training data with worst-case adversarial perturbations for each input. However, these approaches overlook the...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
