Restoring General and Improving Domain-Specific Safety in Fine-Tuned LLMs Without Retraining
Safety-aligned language models are known to suffer degradation in refusal behavior following domain-specific fine-tuning, even when the fine-tuning data is entirely benign.
By Vishnu Kabir Chhabra, Ding Zhu, Zhihui Zhu, Xueru Zhang, Mohammad Mahdi KhaliliarXiv - cs.AI
Read the full story
Originally published by arXiv - cs.AI on Nov 10, 2026.
Comments
Sign in to join the discussion.