MPCb.3

Modular Unlearning in Large Language Models: A Bi-level Optimization Perspective

Jinghan Jia, Yihua Zhang, Michigan State University, United States; Parikshit Ram, Nathalie Baracaldo, IBM research, United States; Sijia Liu, Michigan State University, United States
Session:
MPCb: Generative Models Fine-tuning and Vertical Applications Lecture
Track:
Adaptive Systems, Machine Learning, and Data Analytics
Location:
Chapel
Presentation Time:
Mon, 27 Oct, 11:05 - 11:30 PT (UTC -7)
Presentation
Discussion
Resources
No resources available.
Session MPCb
MPCb.1: Subspace Optimization for Large Language Models with Convergence Guarantees
Kun Yuan, Peking University, China
MPCb.2: Inference-Time Alignment of LLMs via User-Specified Multi-Criteria Transfer Decoding
Mohamad Fares El Hajj Chehade, UT Austin, United States; Soumya Suvra Ghosa, UMD, College park, United States; Souradip Chakraborty, UMD, United States; Avinash Reddy, UCF, United States; Dinesh Manocha, Hao Zhu, Amrit Singh Bedi, UMD, United States
MPCb.3: Modular Unlearning in Large Language Models: A Bi-level Optimization Perspective
Jinghan Jia, Yihua Zhang, Michigan State University, United States; Parikshit Ram, Nathalie Baracaldo, IBM research, United States; Sijia Liu, Michigan State University, United States
MPCb.4: Attention Networks for Spotlight SAR Motion Compensation
Dylan Poppert, Di An, Yu-Ting Kao, Chia-Cheng Hao, David Jansing, Trac Duy Tran, Johns Hopkins University, United States
Contacts