y0news
AnalyticsDigestsSourcesTopicsRSSAICrypto

#safety-preservation News & Analysis

1 article tagged with #safety-preservation. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

1 articles
AINeutralarXiv – CS AI · 6h ago6/10
🧠

Two to Tango: Coupled Task-Reference Selection for Safe LLM Fine-tuning

Researchers propose DualSelect, a framework for fine-tuning large language models that simultaneously selects relevant safety references and compatible task samples to preserve safety alignment while improving task performance. The method achieves significant safety improvements (5.10+ points) across models from 1B to 8B parameters without sacrificing utility.