@inproceedings{yu-etal-2026-joint, title = "Joint Optimization of Training Data and Policy in {RLHF}", author = "Yu, Zhuohao and Zeng, Jiali and Gu, Weizheng and Sun, Mengyuan and Wang, Yidong and Meng, Fandong and Zhou, Jie and Zhang, Shikun and Ye, Wei", editor = "Liakata, Maria and Moreira, Viviane P. and Zhang, Jiajun and Jurgens, David", booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026", month = jul, year = "2026", address = "San Diego, California, United States", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.2109/", pages = "42498--42514", ISBN = "979-8-89176-395-1" }