Reinforcement Learning with Reference-Based Rewards for Language Model Reasoning and Alignment

arXiv:2504.09895 · cs.CL, cs.AI, cs.LG · Submitted 2025-04-14 · Read on arXiv

cs.CL, cs.AI, cs.LG

Submitted: 2025-04-14

Updated: 2026-11-18

Code: https://github.com/mzhaoshuai/RefAlign

Terminology

Sources

Related papers