 Using Interpretation Methods for Model EnhancementConference on Empirical Methods in Natural Language Processing (EMNLP), 2024 |
 REFER: An End-to-end Rationale Extraction Framework for Explanation
RegularizationConference on Computational Natural Language Learning (CoNLL), 2023 |
 XMD: An End-to-End Framework for Interactive Explanation-Based Debugging
of NLP ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Investigating the Benefits of Free-Form RationalesConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 ER-Test: Evaluating Explanation Regularization Methods for Language
ModelsConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
