On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with No Catastrophic Forgetting

Item #:

068431-1179

Details

DOI: https://doi.org/10.52202/068431-1179
Author(s): Marc Dymetman, Hady Elsahar, Tomasz Korbak, Germán Kruszewski
Pages: 16203-16220 (18 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 35
Date/Location: Held 28 November - 9 December 2022, New Orleans, Louisiana, USA.
Series: Advances in Neural Information Processing Systems 35
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

DOI: https://doi.org/10.52202/068431-1179
Author(s): Marc Dymetman, Hady Elsahar, Tomasz Korbak, Germán Kruszewski
Pages: 16203-16220 (18 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 35
Date/Location: Held 28 November - 9 December 2022, New Orleans, Louisiana, USA.
Series: Advances in Neural Information Processing Systems 35
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)