@article{rethinkingharmlessrefusalswhenfinetuning, title = {Rethinking harmless refusals when fine-tuning foundation models}, author = {Florin Pop and Judd Rosenblatt and Diogo Schwerz de Lucena and Michael Vaiana}, year = {2024}, eprint = {2406.19552}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.19552v1}, }