Fan, Y., Hong, Y., Wang, Q., Bao, J., Jiang, H., & Song, Y. (2025). Preference-Oriented Supervised Fine-Tuning: Favoring Target Model over Aligned Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence, 39(22), 23859-23867. https://doi.org/10.1609/aaai.v39i22.34558