3 papers indexed here
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.
Reliable evaluation of large language models (LLMs) is essential for their development and deployment, yet is often costly, risky, and difficult to perform safely online. We study off-policy evaluation for LLMs, where limited human-labeled data from a behavior model are used to evaluate a newer target LLM. This setting...
On-policy distillation (OPD) trains a student on its own rollouts using dense supervision from a teacher. In multi-turn environments, a mistake at a critical decision step can redirect the subsequent rollout toward poor outcomes. We use low teacher confidence on student actions to select high-uncertainty steps for corr...
This work proposes Distilled Preference Probability Policy Optimization (DP3O), an effective and efficient offline alignment algorithm that outperforms state-of-the-art offline methods, achieves performance comparable to iterative DPO, and reduces training time, demonstrating both its effectiveness and efficiency.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
