Qibing Ren, Chang Gao, Jing Shao, Junchi Yan, Xin Tan, Wai Lam, Lizhuang Ma. CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion. In Lun-Wei Ku, Andre Martins, Vivek Srikumar, editors, Findings of the Association for Computational Linguistics, ACL 2024, Bangkok, Thailand and virtual meeting, August 11-16, 2024. pages 11437-11452, Association for Computational Linguistics, 2024. [doi]
@inproceedings{RenGSYTLM24,
title = {CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion},
author = {Qibing Ren and Chang Gao and Jing Shao and Junchi Yan and Xin Tan and Wai Lam and Lizhuang Ma},
year = {2024},
url = {https://aclanthology.org/2024.findings-acl.679},
researchr = {https://researchr.org/publication/RenGSYTLM24},
cites = {0},
citedby = {0},
pages = {11437-11452},
booktitle = {Findings of the Association for Computational Linguistics, ACL 2024, Bangkok, Thailand and virtual meeting, August 11-16, 2024},
editor = {Lun-Wei Ku and Andre Martins and Vivek Srikumar},
publisher = {Association for Computational Linguistics},
isbn = {979-8-89176-099-8},
}