Prompting for explanations improves Adversarial NLI. Is this true? {Yes} it is {true} because {it weakens superficial cues}

Prompting for explanations improves Adversarial NLI. Is this true? {Yes} it is {true} because {it weakens superficial cues} Pride Kavumba author Ana Brassard author Benjamin Heinzerling author Kentaro Inui author 2023-05 text Findings of the Association for Computational Linguistics: EACL 2023 Andreas Vlachos editor Isabelle Augenstein editor Association for Computational Linguistics Dubrovnik, Croatia conference publication kavumba-etal-2023-prompting 10.18653/v1/2023.findings-eacl.162 https://aclanthology.org/2023.findings-eacl.162/ 2023-05 2165 2180