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]
Abstract is missing.