Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging

@inproceedings{farn2025safeguard,
  title = {Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging},
  author = {Hua Farn and Hsuan Su and Shachi H Kumar and Saurav Sahay and Shang-Tse Chen and Hung-yi Lee},
  year = {2025},
  booktitle = {Conference on Empirical Methods in Natural Language Processing},
  eprint = {2412.19512},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.19512},
}