Yi Dong, Zhilin Wang, Makesh Narsimhan Sreedhar, Xianchao Wu, Oleksii Kuchaiev. SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF. In Houda Bouamor, Juan Pino 0001, Kalika Bali, editors, Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023. pages 11275-11288, Association for Computational Linguistics, 2023. [doi]
@inproceedings{DongWSWK23, title = {SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF}, author = {Yi Dong and Zhilin Wang and Makesh Narsimhan Sreedhar and Xianchao Wu and Oleksii Kuchaiev}, year = {2023}, url = {https://aclanthology.org/2023.findings-emnlp.754}, researchr = {https://researchr.org/publication/DongWSWK23}, cites = {0}, citedby = {0}, pages = {11275-11288}, booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023}, editor = {Houda Bouamor and Juan Pino 0001 and Kalika Bali}, publisher = {Association for Computational Linguistics}, isbn = {979-8-89176-061-5}, }