CREST: A Joint Framework for Rationalization and Counterfactual Text Generation
This work addresses the need for more comprehensive interpretability methods in NLP by combining two complementary approaches, offering incremental improvements for model analysis and training.
The paper tackles the problem of integrating selective rationales and counterfactual text generation in NLP by introducing CREST, a joint framework that improves counterfactual quality, model robustness, and interpretability, with results showing more natural counterfactuals and enhanced rationale quality compared to prior methods.
Selective rationales and counterfactual examples have emerged as two effective, complementary classes of interpretability methods for analyzing and training NLP models. However, prior work has not explored how these methods can be integrated to combine their complementary advantages. We overcome this limitation by introducing CREST (ContRastive Edits with Sparse raTionalization), a joint framework for selective rationalization and counterfactual text generation, and show that this framework leads to improvements in counterfactual quality, model robustness, and interpretability. First, CREST generates valid counterfactuals that are more natural than those produced by previous methods, and subsequently can be used for data augmentation at scale, reducing the need for human-generated examples. Second, we introduce a new loss function that leverages CREST counterfactuals to regularize selective rationales and show that this regularization improves both model robustness and rationale quality, compared to methods that do not leverage CREST counterfactuals. Our results demonstrate that CREST successfully bridges the gap between selective rationales and counterfactual examples, addressing the limitations of existing methods and providing a more comprehensive view of a model's predictions.