As NLP models become increasingly integral to decision-making processes, the need for explainability and interpretability has become paramount. In this work, we propose a framework that achieves the aforementioned by generating semantically edited inputs, known as counterfactual interventions, which change the model prediction, thus providing a form of counterfactual explanations for the model. We test our framework on two NLP tasks - binary sentiment classification and topic classification - and show that the generated edits are contrastive, fluent and minimal, while the whole process remains significantly faster that other state-of-the-art counterfactual editors.
@article{arxiv.2408.01969,
title = {Optimal and efficient text counterfactuals using Graph Neural Networks},
author = {Dimitris Lymperopoulos and Maria Lymperaiou and Giorgos Filandrianos and Giorgos Stamou},
journal= {arXiv preprint arXiv:2408.01969},
year = {2025}
}