@inproceedings{wang-etal-2022-identifying,
    title = "Identifying and Mitigating Spurious Correlations for Improving Robustness in {NLP} Models",
    author = "Wang, Tianlu  and
      Sridhar, Rohit  and
      Yang, Diyi  and
      Wang, Xuezhi",
    editor = "Carpuat, Marine  and
      de Marneffe, Marie-Catherine  and
      Meza Ruiz, Ivan Vladimir",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
    month = jul,
    year = "2022",
    address = "Seattle, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.findings-naacl.130",
    doi = "10.18653/v1/2022.findings-naacl.130",
    pages = "1719--1729",
    abstract = "Recently, NLP models have achieved remarkable progress across a variety of tasks; however, they have also been criticized for being not robust. Many robustness problems can be attributed to models exploiting {``}spurious correlations{''}, or {``}shortcuts{''} between the training data and the task labels. Most existing work identifies a limited set of task-specific shortcuts via human priors or error analyses, which requires extensive expertise and efforts. In this paper, we aim to automatically identify such spurious correlations in NLP models at scale. We first leverage existing interpretability methods to extract tokens that significantly affect model{'}s decision process from the input text. We then distinguish {``}genuine{''} tokens and {``}spurious{''} tokens by analyzing model predictions across multiple corpora and further verify them through knowledge-aware perturbations. We show that our proposed method can effectively and efficiently identify a scalable set of {``}shortcuts{''}, and mitigating these leads to more robust models in multiple applications.",
}