Exploring the Trade-off Between Model Performance and Explanation Plausibility of Text Classifiers Using Human Rationales

Lucas Resck, Marcos M. Raimundo, Jorge Poco


Abstract
Saliency post-hoc explainability methods are important tools for understanding increasingly complex NLP models. While these methods can reflect the model’s reasoning, they may not align with human intuition, making the explanations not plausible. In this work, we present a methodology for incorporating rationales, which are text annotations explaining human decisions, into text classification models. This incorporation enhances the plausibility of post-hoc explanations while preserving their faithfulness. Our approach is agnostic to model architectures and explainability methods. We introduce the rationales during model training by augmenting the standard cross-entropy loss with a novel loss function inspired by contrastive learning. By leveraging a multi-objective optimization algorithm, we explore the trade-off between the two loss functions and generate a Pareto-optimal frontier of models that balance performance and plausibility. Through extensive experiments involving diverse models, datasets, and explainability methods, we demonstrate that our approach significantly enhances the quality of model explanations without causing substantial (sometimes negligible) degradation in the original model’s performance.
Anthology ID:
2024.findings-naacl.262
Volume:
Findings of the Association for Computational Linguistics: NAACL 2024
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4190–4216
Language:
URL:
https://aclanthology.org/2024.findings-naacl.262
DOI:
Bibkey:
Cite (ACL):
Lucas Resck, Marcos M. Raimundo, and Jorge Poco. 2024. Exploring the Trade-off Between Model Performance and Explanation Plausibility of Text Classifiers Using Human Rationales. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 4190–4216, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Exploring the Trade-off Between Model Performance and Explanation Plausibility of Text Classifiers Using Human Rationales (Resck et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-naacl.262.pdf
Copyright:
 2024.findings-naacl.262.copyright.pdf