Author of the publication

Guiding LLM to Fool Itself: Automatically Manipulating Machine Reading Comprehension Shortcut Triggers.

, , and . EMNLP (Findings), page 8495-8505. Association for Computational Linguistics, (2023)

Please choose a person to relate this publication to

To differ between persons with the same name, the academic degree and the title of an important publication will be displayed. You can also use the button next to the name to display some publications already assigned to the person.

No persons found for author name Ravfogel, Shauli
add a person with the name Ravfogel, Shauli
 

Other publications of authors with the same name

The Extraordinary Failure of Complement Coercion Crowdsourcing., , , , and . Insights, page 106-116. Association for Computational Linguistics, (2020)Linear Guardedness and its Implications., , and . CoRR, (2022)Ab Antiquo: Proto-language Reconstruction with RNNs., , and . CoRR, (2019)When Bert Forgets How To POS: Amnesic Probing of Linguistic Properties and MLM Predictions., , , and . CoRR, (2020)What Changed? Converting Representational Interventions to Natural Language., , , and . CoRR, (2024)All Roads Lead to Rome? Exploring the Invariance of Transformers' Representations., , , , , , and . CoRR, (2023)Adversarial Concept Erasure in Kernel Space., , , and . EMNLP, page 6034-6055. Association for Computational Linguistics, (2022)LEACE: Perfect linear concept erasure in closed form., , , , , and . CoRR, (2023)The Curious Case of Hallucinatory Unanswerablity: Finding Truths in the Hidden States of Over-Confident Large Language Models., , , , and . CoRR, (2023)Studying the Inductive Biases of RNNs with Synthetic Variations of Natural Languages., , and . NAACL-HLT (1), page 3532-3542. Association for Computational Linguistics, (2019)