@inproceedings{korakakis-vlachos-2023-improving,
    title = "Improving the robustness of {NLI} models with minimax training",
    author = "Korakakis, Michalis  and
      Vlachos, Andreas",
    editor = "Rogers, Anna  and
      Boyd-Graber, Jordan  and
      Okazaki, Naoaki",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.acl-long.801/",
    doi = "10.18653/v1/2023.acl-long.801",
    pages = "14322--14339",
    abstract = "Natural language inference (NLI) models are susceptible to learning shortcuts, i.e. decision rules that spuriously correlate with the label. As a result, they achieve high in-distribution performance, but fail to generalize to out-of-distribution samples where such correlations do not hold. In this paper, we present a training method to reduce the reliance of NLI models on shortcuts and improve their out-of-distribution performance without assuming prior knowledge of the shortcuts being targeted. To this end, we propose a minimax objective between a learner model being trained for the NLI task, and an auxiliary model aiming to maximize the learner{'}s loss by up-weighting examples from regions of the input space where the learner incurs high losses. This process incentivizes the learner to focus on under-represented ``hard'' examples with patterns that contradict the shortcuts learned from the prevailing ``easy'' examples. Experimental results on three NLI datasets demonstrate that our method consistently outperforms other robustness enhancing techniques on out-of-distribution adversarial test sets, while maintaining high in-distribution accuracy."
}