@misc{wang2024conditionedlanguagepolicygeneral, title={Conditioned Language Policy: A General Framework for Steerable Multi-Objective Finetuning}, author={Kaiwen Wang and Rahul Kidambi and Ryan Sullivan and Alekh Agarwal and Christoph Dann and Andrea Michi and Marco Gelmi and Yunxuan Li and Raghav Gupta and Avinava Dubey and Alexandre Ramé and Johan Ferret and Geoffrey Cideron and Le Hou and Hongkun Yu and Amr Ahmed and Aranyak Mehta and Léonard Hussenot and Olivier Bachem and Edouard Leurent}, year={2024}, eprint={2407.15762}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2407.15762}, }