LLM News

Every LLM release, update, and milestone.

Filtered by:rlhf✕ clear
research

BandPO improves LLM reinforcement learning by replacing fixed clipping with probability-aware bounds

Researchers introduce BandPO, a method that replaces the fixed clipping mechanism in PPO with dynamic, probability-aware clipping intervals. The approach addresses a critical limitation: canonical clipping disproportionately suppresses high-advantage tail strategies and causes rapid entropy collapse. Experiments show consistent improvements over standard clipping methods.