13 October 2023
Uh-oh! Fine-tuning LLMs compromises their safety, study finds - 2023-10-13 14:23:38Z
Title:Uh-oh! Fine-tuning LLMs compromises their safety, study finds Summary: Their experiments show that the safety alignment of large language AI models could be significantly undermined when fine-tuned. Link: Uh-oh! Fine-tuning LLMs compromises their safety, study finds
