Yize Cheng, Wenxiao Wang 0002, Mazda Moayeri, Soheil Feizi. DyePack: Provably Flagging Test Set Contamination in LLMs Using Backdoors. In Christos Christodoulopoulos 0001, Tanmoy Chakraborty 0002, Carolyn Rose, Violet Peng, editors, Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, EMNLP 2025, Suzhou, China, November 4-9, 2025. pages 15356-15373, Association for Computational Linguistics, 2025. [doi]
@inproceedings{ChengWMF25,
title = {DyePack: Provably Flagging Test Set Contamination in LLMs Using Backdoors},
author = {Yize Cheng and Wenxiao Wang 0002 and Mazda Moayeri and Soheil Feizi},
year = {2025},
doi = {10.18653/v1/2025.emnlp-main.776},
url = {https://doi.org/10.18653/v1/2025.emnlp-main.776},
researchr = {https://researchr.org/publication/ChengWMF25},
cites = {0},
citedby = {0},
pages = {15356-15373},
booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, EMNLP 2025, Suzhou, China, November 4-9, 2025},
editor = {Christos Christodoulopoulos 0001 and Tanmoy Chakraborty 0002 and Carolyn Rose and Violet Peng},
publisher = {Association for Computational Linguistics},
isbn = {979-8-89176-332-6},
}