@inproceedings{xiong-etal-2025-co,
    title = "Co-{DETECT}: Collaborative Discovery of Edge Cases in Text Classification",
    author = "Xiong, Chenfei  and
      Ni, Jingwei  and
      Fan, Yu  and
      Zouhar, Vil{\'e}m  and
      Rooein, Donya  and
      Calvo-Bartolom{\'e}, Lorena  and
      Hoyle, Alexander Miserlis  and
      Jin, Zhijing  and
      Sachan, Mrinmaya  and
      Leippold, Markus  and
      Hovy, Dirk  and
      El-Assady, Mennatallah  and
      Ash, Elliott",
    editor = {Habernal, Ivan  and
      Schulam, Peter  and
      Tiedemann, J{\"o}rg},
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-demos.25/",
    pages = "354--364",
    ISBN = "979-8-89176-334-0",
    abstract = "We introduce Co-DETECT (Collaborative Discovery of Edge cases in TExt ClassificaTion), a novel mixed-initiative annotation framework that integrates human expertise with automatic annotation guided by large language models (LLMs). Co-DETECT starts with an initial, sketch-level codebook and dataset provided by a domain expert, then leverages the LLM to annotate the data and identify edge cases that are not well described by the initial codebook. Specifically, Co-DETECT flags challenging examples, induces high-level, generalizable descriptions of edge cases, and assists user in incorporating edge case handling rules to improve the codebook. This iterative process enables more effective handling of nuanced phenomena through compact, generalizable annotation rules. Extensive user study, qualitative and quantitative analyses prove the effectiveness of Co-DETECT."
}