A Survey on Natural Language Counterfactual Generation
Abstract: Natural Language Counterfactual generation aims to minimally modify a given text such that the modified text belongs to a different class.
The generated counterfactuals provide insights into the reasoning behind a model's predictions by highlighting which words significantly influence the outcomes. Additionally, they can be used to detect model fairness issues or augment the training data to enhance the model's robustness. A substantial amount of research has been conducted to generate counterfactuals for various NLP tasks, employing different models and methodologies. With the rapid growth of studies in this field, a systematic review is crucial to guide future researchers and developers. To bridge this gap, this survey comprehensively overview textual counterfactual generation methods, particularly including those based on Large Language Models. We propose a new taxonomy that categorizes the generation methods into four groups and systematically summarize the metrics for evaluating the generation quality. Finally, we discuss ongoing research challenges and outline promising directions for future work.
Paper Type: Long
Research Area: Generation
Research Area Keywords: Textual Counterfactual generation;
Contribution Types: Surveys
Languages Studied: English;
Submission Number: 4452
Loading