@inproceedings{chen-etal-2024-self-evolution, title = "Self-Evolution Fine-Tuning for Policy Optimization", author = "Chen, Ruijun and Liang, Jiehao and Gao, Shiping and Wan, Fanqi and Quan, Xiaojun", editor = "Al-Onaizan, Yaser and Bansal, Mohit and Chen, Yun-Nung", booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024", month = nov, year = "2024", address = "Miami, Florida, USA", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/Add-Cong-Liu-Florida-Atlantic-University-author-id/2024.findings-emnlp.238/", doi = "10.18653/v1/2024.findings-emnlp.238", pages = "4120--4137" }