Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection

Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection Jun Yan author Vikas Yadav author Shiyang Li author Lichang Chen author Zheng Tang author Hai Wang author Vijay Srinivasan author Xiang Ren author Hongxia Jin author 2024-06 text Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) Kevin Duh editor Helena Gomez editor Steven Bethard editor Association for Computational Linguistics Mexico City, Mexico conference publication yan-etal-2024-backdooring 10.18653/v1/2024.naacl-long.337 https://aclanthology.org/2024.naacl-long.337/ 2024-06 6065 6086