A Survey on Natural Language Counterfactual Generation

TL;DR

This survey reviews recent methods for generating natural language counterfactuals, emphasizing techniques based on Large Language Models, and discusses evaluation metrics, challenges, and future research directions.

Contribution

It provides a comprehensive taxonomy and overview of NLP counterfactual generation methods, especially those utilizing Large Language Models, guiding future research.

Findings

Categorizes generation methods into four groups

Summarizes evaluation metrics for quality assessment

Highlights challenges and future research directions

Abstract

Natural language counterfactual generation aims to minimally modify a given text such that the modified text will be classified into a different class. The generated counterfactuals provide insight 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 and 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 provides a comprehensive overview of textual counterfactual generation methods, particularly those based on Large Language Models. We propose a new taxonomy that systematically categorizes the generation methods into four groups and summarizes the metrics for evaluating the generation quality. Finally, we discuss ongoing research challenges and outline promising directions for future work.