conftrace_

token-level policy

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

preference model (1) sequence-level optimization (1) reward model training (1) alignment framework (1) hybrid supervision (1) token-level prediction (1) reward model (1) preference modeling (1)

Papers

HAF-RM: A Hybrid Alignment Framework for Reward Model Training ACL 2025