Improving LLM General Preference Alignment via Optimistic Online Mirror Descent
NeurIPSSpotlight2025
TL;DR
Reinforcement learning from human feedback (RLHF) has demonstrated remarkable effectiveness in aligning large language models (LLMs) with human preferences…
Opening excerpt from the authors’ abstract. source
Read the paper
Topics
reinforcement learning large language model language model alignment rlhf llm
← All NeurIPS 2025 Spotlight papers · Browse the whole archive