2026-11-04 DPO — Direct Preference Optimization: Your Language Model is Secretly a Reward Model Agent / Agentic RL
2026-11-04 InstructGPT — Training language models to follow instructions with human feedback Agent / Agentic RL
2026-11-04 DPO — Direct Preference Optimization: Your Language Model is Secretly a Reward Model Agent / Agentic RL
2026-11-04 InstructGPT — Training language models to follow instructions with human feedback Agent / Agentic RL