Lingbo Mo, Boshi Wang, Muhao Chen, Huan Sun 0001. How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities. In Kevin Duh, Helena Gómez-Adorno, Steven Bethard, editors, Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), NAACL 2024, Mexico City, Mexico, June 16-21, 2024. pages 2775-2792, Association for Computational Linguistics, 2024. [doi]
@inproceedings{MoWC024,
title = {How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities},
author = {Lingbo Mo and Boshi Wang and Muhao Chen and Huan Sun 0001},
year = {2024},
doi = {10.18653/v1/2024.naacl-long.152},
url = {https://doi.org/10.18653/v1/2024.naacl-long.152},
researchr = {https://researchr.org/publication/MoWC024},
cites = {0},
citedby = {0},
pages = {2775-2792},
booktitle = {Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), NAACL 2024, Mexico City, Mexico, June 16-21, 2024},
editor = {Kevin Duh and Helena Gómez-Adorno and Steven Bethard},
publisher = {Association for Computational Linguistics},
isbn = {979-8-89176-114-8},
}