Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Chongyu Fan, Jiancheng Liu, Licong Lin, Jinghan Jia, Ruiqi Zhang, Song Mei, Sijia Liu 0001. Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning. In Danielle Belgrave, Cheng Zhang 0005, Laura N. Montoya, Hsuan-Tien Lin, Razvan Pascanu, Piotr Koniusz, Marzyeh Ghassemi, Nancy Chen, Iván Vladimir Meza Ruíz, Arturo Loaiza-Bonilla, editors, Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, NeurIPS 2025, San Diago, CA, USA, December 2-7, 2025 / Mexico City, Mexico, November 30 - December 5, 2025. 2025. [doi]

This author has not been identified. Look up 'Chongyu Fan' in GoogleThis author has not been identified. Look up 'Jiancheng Liu' in GoogleThis author has not been identified. Look up 'Licong Lin' in GoogleThis author has not been identified. Look up 'Jinghan Jia' in GoogleThis author has not been identified. Look up 'Ruiqi Zhang' in GoogleThis author has not been identified. Look up 'Song Mei' in GoogleThis author has not been identified. Look up 'Sijia Liu 0001' in Google

runs on WebDSL