Zhexin Zhang, Jiale Cheng, Hao Sun, Jiawen Deng, Minlie Huang. InstructSafety: A Unified Framework for Building Multidimensional and Explainable Safety Detector through Instruction Tuning. In Houda Bouamor, Juan Pino 0001, Kalika Bali, editors, Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023. pages 10421-10436, Association for Computational Linguistics, 2023. [doi]
@inproceedings{ZhangCSDH23,
title = {InstructSafety: A Unified Framework for Building Multidimensional and Explainable Safety Detector through Instruction Tuning},
author = {Zhexin Zhang and Jiale Cheng and Hao Sun and Jiawen Deng and Minlie Huang},
year = {2023},
url = {https://aclanthology.org/2023.findings-emnlp.700},
researchr = {https://researchr.org/publication/ZhangCSDH23},
cites = {0},
citedby = {0},
pages = {10421-10436},
booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023},
editor = {Houda Bouamor and Juan Pino 0001 and Kalika Bali},
publisher = {Association for Computational Linguistics},
isbn = {979-8-89176-061-5},
}