Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications 事件

Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications arXiv:2605.26133v1 Announce Type: new Abstract: Large Language Models (LLMs) have become the predominant paradigm in NLP, advancing both research and industry. As model sizes and pretraining data grow, concerns about Pretraining Data Exposure (PDE) increase due to the scale and opacity of training datasets. PDE refers to determining whether specific data appeared