Publication
FitCF: A Framework for Automatic Feature Importance-guided Counterfactual Example Generation
Qianli Wang; Nils Feldhus; Simon Ostermann; Luis Felipe Villa Arenas; Sebastian Möller; Vera Schmitt
In: Mohammad Taher Pilehvar; Ekaterina Shutova; Wanxiang Che; Joyce Nabende (Hrsg.). Findings of the Association for Computational Linguistics: ACL 2025. Annual Meeting of the Association for Computational Linguistics (ACL-2025), The 63rd Annual Meeting of the Association for Computational Linguistics, located at ACL 2025 Findings, July 27 - August 1, Vienna, Austria, Association for Computational Linguistics, 2025.
Abstract
Counterfactual examples are widely used in natural language processing (NLP) as valuable data to improve models, and in explainable artificial intelligence (XAI) to understand model behavior. The automated generation of counterfactual examples remains a challenging task even for large language models (LLMs), despite their impressive performance on many tasks. In this paper, we first introduce ZeroCF, a faithful approach for leveraging important words derived from feature attribution methods to generate counterfactual examples in a zero-shot setting. Second, we present a new framework, FitCF, which further verifies aforementioned counterfactuals by label flip verification and then inserts them as demonstrations for few-shot prompting, outperforming two state-of-the-art baselines. Through ablation studies, we identify the importance of each of FitCF's core components in improving the quality of counterfactuals, as assessed through flip rate, perplexity, and similarity measures. Furthermore, we show the effectiveness of LIME and Integrated Gradients as backbone attribution methods for FitCF and find that the number of demonstrations has the largest effect on performance. Finally, we reveal a strong correlation between the faithfulness of feature attribution scores and the quality of generated counterfactuals, which we hope will serve as an important finding for future research in this direction.