"self-play fine-tuning" Papers
2 papers found
Triplets Better Than Pairs: Towards Stable and Effective Self-Play Fine-Tuning for LLMs
Yibo Wang, Hai-Long Sun, Guangda Huzhang et al.
NeurIPS 2025posterarXiv:2601.08198
4
citations
Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
Zixiang Chen, Yihe Deng, Huizhuo Yuan et al.
ICML 2024poster