ACL · 2026 · Conference paper

AGTAO: Robust and Stabilized LLM Unlearning via Adversarial Gating Training with Adaptive Orthogonality

Pengyu Li, Lingling Zhang, Zhitao Gao, Yanrui Wu, Yuxuan Dong, Huan Liu, Bifan Wei, Jun Liu

Rendered by arXiv from the LaTeX source. If anything looks wrong, switch to the PDF.HTML · PDF · Open in a new tab ↗ · Close

Published in: Annual Meeting of the Association for Computational Linguistics
Date: 2026-02-02
Citations: 1
arXiv: 2602.01703 ↗

Cite

@inproceedings{li2026agtao,
  title = {AGTAO: Robust and Stabilized LLM Unlearning via Adversarial Gating Training with Adaptive Orthogonality},
  author = {Pengyu Li and Lingling Zhang and Zhitao Gao and Yanrui Wu and Yuxuan Dong and Huan Liu and Bifan Wei and Jun Liu},
  year = {2026},
  booktitle = {Annual Meeting of the Association for Computational Linguistics},
  eprint = {2602.01703},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.01703},
}