@inproceedings{santosh-etal-2022-deconfounding,
    title = "Deconfounding Legal Judgment Prediction for {E}uropean Court of Human Rights Cases Towards Better Alignment with Experts",
    author = "Santosh, T.y.s.s  and
      Xu, Shanshan  and
      Ichim, Oana  and
      Grabmair, Matthias",
    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.emnlp-main.74",
    pages = "1120--1138",
    abstract = "This work demonstrates that Legal Judgement Prediction systems without expert-informed adjustments can be vulnerable to shallow, distracting surface signals that arise from corpus construction, case distribution, and confounding factors. To mitigate this, we use domain expertise to strategically identify statistically predictive but legally irrelevant information. We adopt adversarial training to prevent the system from relying on it. We evaluate our deconfounded models by employing interpretability techniques and comparing to expert annotations. Quantitative experiments and qualitative analysis show that our deconfounded model consistently aligns better with expert rationales than baselines trained for prediction only. We further contribute a set of reference expert annotations to the validation and testing partitions of an existing benchmark dataset of European Court of Human Rights cases.",
}