today local_bar

Xiang Kong

Researcher, Apple

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 4

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Checklists Are Better Than Reward Models For Aligning Language Models

#103 Spotlight · Vijay Viswanathan, Yanchao Sun, Xiang Kong, Meng Cao, Graham Neubig, Tongshuang Wu

We show that using checklists to automatically grade responses for reinforcement learning leads to improved instruction following