BLUR: A Bi-Level Optimization Approach for LLM Unlearning

BLUR: A Bi-Level Optimization Approach for LLM Unlearning

Hadi Reisizadeh, Jinghan Jia, Zhiqi Bu, Bhanukiran Vinzamuri, Anil Ramakrishna, Kai-Wei Chang, Volkan Cevher, Sijia Liu, and Mingyi Hong, in EACL, 2026.

Code

Download the full text

---

Abstract

• Source Code

---

Bib Entry

@inproceedings{reisizadeh2026blur,
  title = {BLUR: A Bi-Level Optimization Approach for LLM Unlearning},
  author = {Reisizadeh, Hadi and Jia, Jinghan and Bu, Zhiqi and Vinzamuri, Bhanukiran and Ramakrishna, Anil and Chang, Kai-Wei and Cevher, Volkan and Liu, Sijia and Hong, Mingyi},
  booktitle = {EACL},
  year = {2026}
}

---

Related Publications

1. Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning, EMNLP-Finding, 2025
2. LUME: LLM Unlearning with Multitask Evaluations, EMNLP-Finding, 2025
3. Unlearning as Multi-task Optimization: A Normalized Gradient Difference Approach with an Adaptive Learning Rate, NAACL, 2025