From Unfamiliar to Familiar: Detecting Pre-training Data via Gradient Deviations in Large Language Models 事件

From Unfamiliar to Familiar: Detecting Pre-training Data via Gradient Deviations in Large Language Models arXiv:2603.04828v2 Announce Type: replace Abstract: Pre-training data detection for LLMs is essential for addressing copyright concerns and mitigating benchmark contamination. Existing methods mainly focus on the likelihood-based statistical features or heuristic signals before and after fine-tuning, but the former are susceptible to word frequency bias in corpora, and the latter strongly d