@article{phi3safetyposttrainingaligninglanguage, title = {Phi-3 Safety Post-Training: Aligning Language Models with a "Break-Fix" Cycle}, author = {Emman Haider and Daniel Perez-Becker and Thomas Portet and Piyush Madan and Amit Garg and Atabak Ashfaq and David Majercak and Wen Wen and Dongwoo Kim and ZiYi Yang and Jianwen Zhang and Hiteshi Sharma and Blake Bullwinkel and Martin Pouliot and Amanda Minnich and Shiven Chawla and Solianna Herrera and Shahed Warreth and Maggie Engler and Gary Lopez and Nina Chikanov and Raja Sekhar Rao Dheekonda and Bolor-Erdene Jagdagdorj and Roman Lutz and Richard Lundeen and Tori Westerhoff and Pete Bryan and Christian Seifert and Ram Shankar Siva Kumar and Andrew Berkley and Alex Kessler}, year = {2024}, eprint = {2407.13833}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2407.13833v2}, }