Checklists Are Better Than Reward Models For Aligning Language Models

NeurIPSSpotlight2025

Authors: Vijay Viswanathan, Yanchao Sun, Xiang Kong, Meng Cao, Graham Neubig, Tongshuang Wu
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

Language models must be adapted to understand and follow user instructions…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

language model

← All NeurIPS 2025 Spotlight papers · Browse the whole archive