arXiv · 2025 · Preprint

Preventing Catastrophic Forgetting: Behavior-Aware Sampling for Safer Language Model Fine-Tuning

Anh C. Pham, Mihir Thalanki, Michael Sun, Aditya Chaloo, Ankita Gupta, Tian Xia, Aditya Mate, Ehimwenma Nosakhare, Soundararajan Srinivasan

Rendered by arXiv from the LaTeX source. If anything looks wrong, switch to the PDF.HTML · PDF · Open in a new tab ↗ · Close
Date
2025-10-23
Citations
1
arXiv
2510.21885
Cite
@misc{pham2025preventing,
  title = {Preventing Catastrophic Forgetting: Behavior-Aware Sampling for Safer Language Model Fine-Tuning},
  author = {Anh C. Pham and Mihir Thalanki and Michael Sun and Aditya Chaloo and Ankita Gupta and Tian Xia and Aditya Mate and Ehimwenma Nosakhare and Soundararajan Srinivasan},
  year = {2025},
  eprint = {2510.21885},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.21885},
}