AINeutralarXiv – CS AI · 6h ago6/10
🧠
S-SPPO: Semantic-Calibrated Self-Play Preference Optimization
Researchers propose S-SPPO, an improved framework for aligning large language models with human preferences that addresses instability issues in Self-Play Preference Optimization. The method uses semantic calibration techniques to prevent policy degradation when the model generates semantically similar responses, achieving competitive performance on AlpacaEval 2.0 without additional human annotations.
🧠 Llama