@inproceedings{long-etal-2025-truthful, title = "When Truthful Representations Flip Under Deceptive Instructions?", author = "Long, Xianxuan and Fu, Yao and Li, Runchao and Sheng, Mu and Yu, Haotian and Han, Xiaotian and Li, Pan", editor = "Christodoulopoulos, Christos and Chakraborty, Tanmoy and Rose, Carolyn and Peng, Violet", booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing", month = nov, year = "2025", address = "Suzhou, China", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.826/", pages = "16326--16346", ISBN = "979-8-89176-332-6" }