Towards Benchmarking the Utility of Explanations for Model Debugging Maximilian Idahl author Lijun Lyu author Ujwal Gadiraju author Avishek Anand author 2021-06 text Proceedings of the First Workshop on Trustworthy Natural Language Processing Yada Pruksachatkun editor Anil Ramakrishna editor Kai-Wei Chang editor Satyapriya Krishna editor Jwala Dhamala editor Tanaya Guha editor Xiang Ren editor Association for Computational Linguistics Online conference publication idahl-etal-2021-towards 10.18653/v1/2021.trustnlp-1.8 https://aclanthology.org/2021.trustnlp-1.8/ 2021-06 68 73