Cross-Task Defense: Instruction-Tuning LLMs for Content Safety Yu Fu author Wen Xiao author Jia Chen author Jiachen Li author Evangelos Papalexakis author Aichi Chien author Yue Dong author 2024-06 text Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024) Anaelia Ovalle editor Kai-Wei Chang editor Yang Trista Cao editor Ninareh Mehrabi editor Jieyu Zhao editor Aram Galstyan editor Jwala Dhamala editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Mexico City, Mexico conference publication fu-etal-2024-cross 10.18653/v1/2024.trustnlp-1.9 https://aclanthology.org/2024.trustnlp-1.9/ 2024-06 85 93