SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

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]

This author has not been identified. Look up 'Yi Dong' in GoogleThis author has not been identified. Look up 'Zhilin Wang' in GoogleThis author has not been identified. Look up 'Makesh Narsimhan Sreedhar' in GoogleThis author has not been identified. Look up 'Xianchao Wu' in GoogleThis author has not been identified. Look up 'Oleksii Kuchaiev' in Google

runs on WebDSL