AINeutralarXiv – CS AI · 7h ago6/10
🧠
DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning
Researchers introduce DataShield, a novel method for identifying safety-degrading samples in benign datasets used to fine-tune large language models. The approach efficiently detects data points that compromise LLM safety through compliance vector analysis, addressing a critical vulnerability in current model training practices.
🧠 Llama