Faithfulness Tests for Natural Language Explanations
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Documents
- Fulltext
Final published version, 296 KB, PDF document
Explanations of neural models aim to reveal a model’s decision-making process for its predictions. However, recent work shows that current methods giving explanations such as saliency maps or counterfactuals can be misleading, as they are prone to present reasons that are unfaithful to the model’s inner workings. This work explores the challenging question of evaluating the faithfulness of natural language explanations (NLEs). To this end, we present two tests. First, we propose a counterfactual input editor for inserting reasons that lead to counterfactual predictions but are not reflected by the NLEs. Second, we reconstruct inputs from the reasons stated in the generated NLEs and check how often they lead to the same predictions. Our tests can evaluate emerging NLE models, proving a fundamental tool in the development of faithful NLEs.
Original language | English |
---|---|
Title of host publication | Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) |
Number of pages | 12 |
Publisher | Association for Computational Linguistics (ACL) |
Publication date | 2023 |
Pages | 283-294 |
ISBN (Electronic) | 9781959429715 |
DOIs | |
Publication status | Published - 2023 |
Event | 61st Annual Meeting of the Association for Computational Linguistics, ACL 2023 - Toronto, Canada Duration: 9 Jul 2023 → 14 Jul 2023 |
Conference
Conference | 61st Annual Meeting of the Association for Computational Linguistics, ACL 2023 |
---|---|
Land | Canada |
By | Toronto |
Periode | 09/07/2023 → 14/07/2023 |
Sponsor | Bloomberg Engineering, et al., Google Research, Liveperson, Meta, Microsoft |
Bibliographical note
Publisher Copyright:
© 2023 Association for Computational Linguistics.
Number of downloads are based on statistics from Google Scholar and www.ku.dk
ID: 369552736