Abstract
Recent work in Natural Language Processing has focused on developing approaches that extract faithful explanations, either via identifying the most important tokens in the input (i.e. post-hoc explanations) or by designing inherently faithful models that first select the most important tokens and then use them to predict the correct label (i.e. select-then-predict models). Currently, these approaches are largely evaluated on in-domain settings. Yet, little is known about how post-hoc explanations and inherently faithful models perform in out-of-domain settings. In this paper, we conduct an extensive empirical study that examines: (1) the out-of-domain faithfulness of post-hoc explanations, generated by five feature attribution methods; and (2) the out-of-domain performance of two inherently faithful models over six datasets. Contrary to our expectations, results show that in many cases out-of-domain post-hoc explanation faithfulness measured by sufficiency and comprehensiveness is higher compared to in-domain. We find this misleading and suggest using a random baseline as a yardstick for evaluating post-hoc explanation faithfulness. Our findings also show that select-then predict models demonstrate comparable predictive performance in out-of-domain settings to full-text trained models.- Anthology ID:
- 2022.acl-long.477
- Volume:
- Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Editors:
- Smaranda Muresan, Preslav Nakov, Aline Villavicencio
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6920–6938
- Language:
- URL:
- https://aclanthology.org/2022.acl-long.477
- DOI:
- 10.18653/v1/2022.acl-long.477
- Cite (ACL):
- George Chrysostomou and Nikolaos Aletras. 2022. An Empirical Study on Explanations in Out-of-Domain Settings. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6920–6938, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- An Empirical Study on Explanations in Out-of-Domain Settings (Chrysostomou & Aletras, ACL 2022)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2022.acl-long.477.pdf
- Code
- gchrysostomou/ood_faith
- Data
- IMDb Movie Reviews, SST