2 papers
cs.LG2026
EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL
Lunjun Zhang, Jimmy Ba
Reinforcement Learning (RL) has enabled Large Language Models (LLMs) to acquire increasingly complex reasoning and agentic behaviors. In this work, we propose two simple techniques…
cs.LG2024
The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
Nathaniel Li, Alexander Pan, Anjali Gopal +54
The White House Executive Order on Artificial Intelligence highlights the risks of large language models (LLMs) empowering malicious actors in developing biological, cyber, and che…