@inproceedings{demir-canbaz-2025-validate,
    title = "Validate Your Authority: Benchmarking {LLM}s on Multi-Label Precedent Treatment Classification",
    author = "Demir, M. Mikail  and
      Canbaz, M Abdullah",
    editor = "Aletras, Nikolaos  and
      Chalkidis, Ilias  and
      Barrett, Leslie  and
      Goanț{\u{a}}, C{\u{a}}t{\u{a}}lina  and
      Preoțiuc-Pietro, Daniel  and
      Spanakis, Gerasimos",
    booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.nllp-1.13/",
    doi = "10.18653/v1/2025.nllp-1.13",
    pages = "172--183",
    ISBN = "979-8-89176-338-8",
    abstract = "Automating the classification of negative treatment in legal precedent is a critical yet nuanced NLP task where misclassification carries significant risk. To address the shortcomings of standard accuracy, this paper introduces a more robust evaluation framework. We benchmark modern Large Language Models on a new, expert-annotated dataset of 239 real-world legal citations and propose a novel Average Severity Error metric to better measure the practical impact of classification errors. Our experiments reveal a performance split: Google{'}s Gemini 2.5 Flash achieved the highest accuracy on a high-level classification task (79.1{\%}), while OpenAI{'}s GPT-5-mini was the top performer on the more complex fine-grained schema (67.7{\%}). This work establishes a crucial baseline, provides a new context-rich dataset, and introduces an evaluation metric tailored to the demands of this complex legal reasoning task."
}