“Honey, Tell Me What’s Wrong”, Global Explanation of Textual Discriminative Models through Cooperative Generation

Antoine Chaffin, Julien Delaunay

Abstract
The ubiquity of complex machine learning has raised the importance of model-agnostic explanation algorithms. These methods create artificial instances by slightly perturbing real instances, capturing shifts in model decisions. However, such methods rely on initial data and only provide explanations of the decision for these. To tackle these problems, we propose Therapy, the first global and model-agnostic explanation method adapted to text which requires no input dataset. Therapy generates texts following the distribution learned by a classifier through cooperative generation. Because it does not rely on initial samples, it allows to generate explanations even when data is absent (e.g., for confidentiality reasons). Moreover, conversely to existing methods that combine multiple local explanations into a global one, Therapy offers a global overview of the model behavior on the input space. Our experiments show that although using no input data to generate samples, Therapy provides insightful information about features used by the classifier that is competitive with the ones from methods relying on input samples and outperforms them when input samples are not specific to the studied model.
Anthology ID:
2023.blackboxnlp-1.6
Volume:
Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP
Month:
December
Year:
2023
Address:
Singapore
Editors:
Yonatan Belinkov, Sophie Hao, Jaap Jumelet, Najoung Kim, Arya McCarthy, Hosein Mohebbi
Venues:
BlackboxNLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
76–88
Language:
URL:
https://aclanthology.org/2023.blackboxnlp-1.6
DOI:
10.18653/v1/2023.blackboxnlp-1.6
Bibkey:
Cite (ACL):
Antoine Chaffin and Julien Delaunay. 2023. “Honey, Tell Me What’s Wrong”, Global Explanation of Textual Discriminative Models through Cooperative Generation. In Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, pages 76–88, Singapore. Association for Computational Linguistics.
Cite (Informal):
“Honey, Tell Me What’s Wrong”, Global Explanation of Textual Discriminative Models through Cooperative Generation (Chaffin & Delaunay, BlackboxNLP-WS 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2023.blackboxnlp-1.6.pdf
PDF Search