Counterfactuals of Counterfactuals: a back-translation-inspired approach to analyse counterfactual editors

George Filandrianos, Edmund Dervakos, Orfeas Menis Mastromichalakis, Chrysoula Zerva, Giorgos Stamou


Abstract
In the wake of responsible AI, interpretability methods, which attempt to provide an explanation for the predictions of neural models have seen rapid progress. In this work, we are concerned with explanations that are applicable to natural language processing (NLP) models and tasks, and we focus specifically on the analysis of counterfactual, contrastive explanations. We note that while there have been several explainers proposed to produce counterfactual explanations, their behaviour can vary significantly and the lack of a universal ground truth for the counterfactual edits imposes an insuperable barrier on their evaluation. We propose a new back translation-inspired evaluation methodology that utilises earlier outputs of the explainer as ground truth proxies to investigate the consistency of explainers. We show that by iteratively feeding the counterfactual to the explainer we can obtain valuable insights into the behaviour of both the predictor and the explainer models, and infer patterns that would be otherwise obscured. Using this methodology, we conduct a thorough analysis and propose a novel metric to evaluate the consistency of counterfactual generation approaches with different characteristics across available performance indicators.
Anthology ID:
2023.findings-acl.606
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9507–9525
Language:
URL:
https://aclanthology.org/2023.findings-acl.606
DOI:
10.18653/v1/2023.findings-acl.606
Bibkey:
Cite (ACL):
George Filandrianos, Edmund Dervakos, Orfeas Menis Mastromichalakis, Chrysoula Zerva, and Giorgos Stamou. 2023. Counterfactuals of Counterfactuals: a back-translation-inspired approach to analyse counterfactual editors. In Findings of the Association for Computational Linguistics: ACL 2023, pages 9507–9525, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Counterfactuals of Counterfactuals: a back-translation-inspired approach to analyse counterfactual editors (Filandrianos et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.606.pdf
Video:
 https://aclanthology.org/2023.findings-acl.606.mp4