Restoring General and Improving Domain-Specific Safety in Fine-Tuned LLMs Without Retraining
arXiv:2611.10279v1 Announce Type: new Abstract: 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. The predominant mitigation strategy, preference optimization on the fine-tuned model, is…
Excerpt provided by arXiv cs.AI via its public feed. Full reporting belongs to the original publisher.
Read the full story on arXiv cs.AI
Related coverage
TechCrunch AI · 9m ago
PSI is trying to make a business out of AI-driven scientific discovery
The Decoder · 53m ago
Gemini 4 Carbon arrives just in time to feel like yesterdays news in the fastest model cycle yet
Ars Technica AI · 4h ago
DeepMind reveals Gemini Robotics 2.5 and open safety benchmark "ASIMOV-jailbreak"
Google DeepMind · 7h ago
Introducing AlphaProof Code: a breakthrough in verifying complex software at depth