Work

BLUR: A Bi-Level Optimization Approach for LLM Unlearning

Year: 2026

Type: conference-paper

Abstract: Hadi Reisizadeh, Jinghan Jia, Zhiqi Bu, Bhanukiran Vinzamuri, Anil Ramakrishna, Kai-Wei Chang, Volkan Cevher, Sijia Liu, Mingyi Hong. Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Source: Conference of the European Chapter of the Association for Computational Linguistics

DOI: 10.18653/v1/2026.eacl-long.331

Authors: Hadi Reisizadeh, Jinghan Jia, Zhiqi Bu, Bhanukiran Vinzamuri, Anil Ramakrishna, Kai-Wei Chang, Volkan Cevher, Sijia Liu, Mingyi Hong

Institutions: University of Minnesota, Michigan State University, University of California, Los Angeles, École Polytechnique Fédérale de Lausanne

Language: English

Topic: Privacy-Preserving Technologies in Data

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: National Science Foundation

Awards: Collaborative Research: III: Medium: Advancing Large Language Model Unlearning: Foundations and Applications, Bi-Level Optimization for Hierarchical Machine Learning Problems: Models, Algorithms and Applications, Collaborative Research: SLES: Verifying and Enforcing Safety Constraints in AI-based Sequential Generation

OpenAlex ID: W7140077777

FWCI: 8.936

Cites:

Cited by: 1

Related to: 10