@inproceedings{srikanth-rudinger-2022-partial,
    title = "Partial-input baselines show that {NLI} models can ignore context, but they don{'}t.",
    author = "Srikanth, Neha  and
      Rudinger, Rachel",
    editor = "Carpuat, Marine  and
      de Marneffe, Marie-Catherine  and
      Meza Ruiz, Ivan Vladimir",
    booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
    month = jul,
    year = "2022",
    address = "Seattle, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2022.naacl-main.350/",
    doi = "10.18653/v1/2022.naacl-main.350",
    pages = "4753--4763",
    abstract = "When strong partial-input baselines reveal artifacts in crowdsourced NLI datasets, the performance of full-input models trained on such datasets is often dismissed as reliance on spurious correlations. We investigate whether state-of-the-art NLI models are capable of overriding default inferences made by a partial-input baseline. We introduce an evaluation set of 600 examples consisting of perturbed premises to examine a RoBERTa model{'}s sensitivity to edited contexts. Our results indicate that NLI models are still capable of learning to condition on context{---}a necessary component of inferential reasoning{---}despite being trained on artifact-ridden datasets."
}