Atanasova, P;
Camburu, OM;
Lioma, C;
Lukasiewicz, T;
Simonsen, JG;
Augenstein, I;
(2023)
Faithfulness Tests for Natural Language Explanations.
In:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers).
(pp. pp. 283-294).
Association for Computational Linguistics (ACL): Toronto, Canada.
Preview |
Text
Camburu_2023.acl-short.25.pdf Download (302kB) | Preview |
Abstract
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.
| Type: | Proceedings paper |
|---|---|
| Title: | Faithfulness Tests for Natural Language Explanations |
| Event: | 61st Annual Meeting of the Association for Computational Linguistics |
| ISBN-13: | 9781959429715 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.18653/v1/2023.acl-short.25 |
| Publisher version: | http://dx.doi.org/10.18653/v1/2023.acl-short.25 |
| Language: | English |
| Additional information: | ACL materials are Copyright © 1963–2023 ACL; other materials are copyrighted by their respective copyright holders. Materials prior to 2016 here are licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 3.0 International License. Permission is granted to make copies for the purposes of teaching and research. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10178606 |
Archive Staff Only
 |
View Item |
