Yifan Lan, Yuanpu Cao, Weitong Zhang, Lu Lin 0001, Jinghui Chen. Phi: Preference Hijacking in Multi-modal Large Language Models at Inference Time. 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 17840-17865, Association for Computational Linguistics, 2025. [doi]
Abstract is missing.