NeurIPS · 2024 · Journal article · Top venue

Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference

Jiabao Ji, Yujian Liu, Yang Zhang, Gaowen Liu, Ramana Rao Kompella, Sijia Liu, Shiyu Chang

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
Neural Information Processing Systems
Date
2024-06-12
Citations
100
arXiv
2406.08607
Cite
@article{ji2024reversing,
  title = {Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference},
  author = {Jiabao Ji and Yujian Liu and Yang Zhang and Gaowen Liu and Ramana Rao Kompella and Sijia Liu and Shiyu Chang},
  year = {2024},
  journal = {Neural Information Processing Systems},
  eprint = {2406.08607},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.08607},
}