Peter Hase, Shiyue Zhang, Harry Xie, Mohit Bansal. Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?. In Trevor Cohn, Yulan He, Yang Liu, editors, Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings, EMNLP 2020, Online Event, 16-20 November 2020. pages 4351-4367, Association for Computational Linguistics, 2020. [doi]
Abstract is missing.