EXPLAIN, EDIT, GENERATE: Rationale-Sensitive Counterfactual Data Augmentation for Multi-hop Fact Verification
Automatic multi-hop fact verification task has gained significant attention in recent years. Despite impressive results, these well-designed models perform poorly on out-of-domain data. One possible solution is to augment the training data with counterfactuals, which are generated by minimally altering the causal features of the original data. However, current counterfactual data augmentation techniques fail to handle multi-hop fact verification due to their incapability to preserve the complex logical relationships within multiple correlated texts. In this paper, we overcome this limitation by developing a rationale-sensitive method to generate linguistically diverse and label-flipping counterfactuals while preserving logical relationships. In specific, the diverse and fluent counterfactuals are generated via an Explain-Edit-Generate architecture. Moreover, the checking and filtering modules are proposed to regularize the counterfactual data with logical relations and flipped labels. Experimental results show that the proposed approach outperforms the SOTA baselines and can generate linguistically diverse counterfactual data without disrupting their logical relationships.
Code (1)
Tasks
counterfactualData AugmentationFact VerificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
CREST: A Joint Framework for Rationalization and Counterfactual Text Generation
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 meth…
counterfactualData AugmentationText GenerationvalidInterpretable Credit Application Predictions With Counterfactual Explanations
We predict credit applications with off-the-shelf, interchangeable black-box classifiers and we explain single predictions with counterfactual explanations. Counterfactual explanations expose the minimal changes required…
counterfactualOptimal and efficient text counterfactuals using Graph Neural Networks
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 gen…
counterfactualDecision MakingSentiment AnalysisSentiment Classification+1Graph Edits for Counterfactual Explanations: A comparative study
Counterfactuals have been established as a popular explainability technique which leverages a set of minimal edits to alter the prediction of a classifier. When considering conceptual counterfactuals on images, the edits…
counterfactualGraph Neural NetworkKnowledge GraphsHyConEx: Hypernetwork classifier with counterfactual explanations
In recent years, there has been a growing interest in explainable AI methods. We want not only to make accurate predictions using sophisticated neural networks but also to understand what the model's decision is based on…
counterfactual