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. and Sanyal, A. and Dokania, P. K. |
| Book Title: | Advances in Neural Information Processing Systems 37 (NeurIPS 2024) |
| Year: | 2024 |
| Month: | December |
| Department(s): | Empirische Inferenz |
| Bibtex Type: | Conference Paper (conference) |
| Event Name: | 38th Annual Conference on Neural Information Processing Systems |
| Event Place: | Vancouver, Canada |
| State: | Accepted |
|
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. and Sanyal, A. and Dokania, P. K.},
booktitle = {Advances in Neural Information Processing Systems 37 (NeurIPS 2024)},
month = dec,
year = {2024},
doi = {},
month_numeric = {12}
}
|
|
