Mosh Levy, Shauli Ravfogel, Yoav Goldberg. Guiding LLM to Fool Itself: Automatically Manipulating Machine Reading Comprehension Shortcut Triggers. In Houda Bouamor, Juan Pino 0001, Kalika Bali, editors, Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023. pages 8495-8505, Association for Computational Linguistics, 2023. [doi]
@inproceedings{LevyRG23,
title = {Guiding LLM to Fool Itself: Automatically Manipulating Machine Reading Comprehension Shortcut Triggers},
author = {Mosh Levy and Shauli Ravfogel and Yoav Goldberg},
year = {2023},
url = {https://aclanthology.org/2023.findings-emnlp.569},
researchr = {https://researchr.org/publication/LevyRG23},
cites = {0},
citedby = {0},
pages = {8495-8505},
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},
}