Alex Mei, Sharon Levy, William Yang Wang. ASSERT: Automated Safety Scenario Red Teaming for Evaluating the Robustness of Large Language Models. In Houda Bouamor, Juan Pino 0001, Kalika Bali, editors, Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023. pages 5831-5847, Association for Computational Linguistics, 2023. [doi]
@inproceedings{MeiLW23-1, title = {ASSERT: Automated Safety Scenario Red Teaming for Evaluating the Robustness of Large Language Models}, author = {Alex Mei and Sharon Levy and William Yang Wang}, year = {2023}, url = {https://aclanthology.org/2023.findings-emnlp.388}, researchr = {https://researchr.org/publication/MeiLW23-1}, cites = {0}, citedby = {0}, pages = {5831-5847}, 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}, }