Skip to content
conftrace_

kl penalty

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

critical token (1) large language model (1) reinforcement learning fine-tuning (1) token-level exploration (1) reward signal (1) kl divergence (1) policy optimization (1)

Papers

Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning NAACL 2025