AIBullisharXiv – CS AI · Mar 37/106
🧠
Token-level Data Selection for Safe LLM Fine-tuning
Researchers have developed TOSS, a new framework for safely fine-tuning large language models that operates at the token level rather than sample level. The method identifies and removes unsafe tokens while preserving task-specific information, demonstrating superior performance compared to existing sample-level defense methods in maintaining both safety and utility.