Tianyi Li, Mohammad Javad Hosseini, Sabine Weber, Mark Steedman. Language Models Are Poor Learners of Directional Inference. In Yoav Goldberg, Zornitsa Kozareva, Yue Zhang, editors, Findings of the Association for Computational Linguistics: EMNLP 2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022. pages 903-921, Association for Computational Linguistics, 2022. [doi]
Abstract is missing.