Detecting Training Data of Large Language Models via Expectation Maximization

Gyuwan Kim, Yang Li, Evangelia Spiliopoulou, Jie Ma, William Yang Wang. Detecting Training Data of Large Language Models via Expectation Maximization. In Vera Demberg, Kentaro Inui, LluĂ­s Marquez, editors, Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2026 - Volume 1: Long Papers, Rabat, Morocco, March 24-29, 2026. pages 1115-1129, Association for Computational Linguistics, 2026. [doi]

Authors

Gyuwan Kim

This author has not been identified. Look up 'Gyuwan Kim' in Google

Yang Li

This author has not been identified. Look up 'Yang Li' in Google

Evangelia Spiliopoulou

This author has not been identified. Look up 'Evangelia Spiliopoulou' in Google

Jie Ma

This author has not been identified. Look up 'Jie Ma' in Google

William Yang Wang

This author has not been identified. Look up 'William Yang Wang' in Google