NAACL · 2024 · Conference paper

UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models

Yijiang River Dong, Hongzhou Lin, Mikhail Belkin, R. Huerta, Ivan Vuli'c

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
North American Chapter of the Association for Computational Linguistics
Date
2024-02-15
Citations
55
arXiv
2402.10052
Cite
@inproceedings{dong2024undial,
  title = {UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models},
  author = {Yijiang River Dong and Hongzhou Lin and Mikhail Belkin and R. Huerta and Ivan Vuli'c},
  year = {2024},
  booktitle = {North American Chapter of the Association for Computational Linguistics},
  eprint = {2402.10052},
  archivePrefix = {arXiv},
  doi = {10.18653/v1/2025.naacl-long.444},
  url = {https://arxiv.org/abs/2402.10052},
}