@article{languagemodelsarehomersimpsonsafetyre, title = {Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic}, author = {Rishabh Bhardwaj and Do Duc Anh and Soujanya Poria}, year = {2024}, eprint = {2402.11746}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2402.11746v1}, }