Gradient Ascent Post-training Enhances Language Model Generalization

Dongkeun Yoon, Joel Jang, Sungdong Kim, Minjoon Seo. Gradient Ascent Post-training Enhances Language Model Generalization. In Anna Rogers, Jordan L. Boyd-Graber, Naoaki Okazaki, editors, Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), ACL 2023, Toronto, Canada, July 9-14, 2023. pages 851-864, Association for Computational Linguistics, 2023. [doi]

Authors

Dongkeun Yoon

This author has not been identified. Look up 'Dongkeun Yoon' in Google

Joel Jang

This author has not been identified. Look up 'Joel Jang' in Google

Sungdong Kim

This author has not been identified. Look up 'Sungdong Kim' in Google

Minjoon Seo

This author has not been identified. Look up 'Minjoon Seo' in Google