Verified record · from the answer index

simpo-training

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler,

skill:orchestra-research/ai-research-skills/simpo-training · published by orchestra-research · source repository