Header logo is

What Makes Safety Fine-tuning Methods Safe? A Mechanistic Study

2024

Conference Paper

ei


Author(s): Jain, S. and Lubana, E. S. and Oksuz, K. and Joy, T. and Torr, P. H. S. and Sanyal, A. and Dokania, P. K.
Book Title: ICML 2024 Workshop on Mechanistic Interpretability (Spotlight)
Year: 2024
Month: July

Department(s): Empirische Inferenz
Bibtex Type: Conference Paper (conference)

Event Place: Vienna, Austria

State: Published
URL: https://openreview.net/forum?id=BS2CbUkJpy

BibTex

@conference{Jainetal24,
  title = {What Makes Safety Fine-tuning Methods Safe? A Mechanistic Study},
  author = {Jain, S. and Lubana, E. S. and Oksuz, K. and Joy, T. and Torr, P. H. S. and Sanyal, A. and Dokania, P. K.},
  booktitle = {ICML 2024 Workshop on Mechanistic Interpretability (Spotlight)},
  month = jul,
  year = {2024},
  doi = {},
  url = {https://openreview.net/forum?id=BS2CbUkJpy},
  month_numeric = {7}
}