Skip to content

Author

W. Sun

We have 2 of 62 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.

Dual Active Learning for Reinforcement Learning from Human Feedback

This paper first proposes a dual active reward learning algorithm for the simultaneous selection of conversations and teachers, and applies pessimistic RL to solve the alignment problem, based on the learned reward estimator.

Pang-Pang Liu, Cheng-Chun Shi, W. Sun · 28 citations · ⚡2

LLM Evaluation as Tensor Completion: Low Rank Structure and Semiparametric Efficiency

A score-whitening method that equalizes local Fisher information and restores stable inference at the optimal sample-complexity scale is introduced that provides a principled framework for uncertainty quantification in LLM evaluation and more broadly for inference on low-rank structures from pairwise data.

Jiachun Li, David Simchi-Levi, W. Sun · 2 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.