@inproceedings{ho-etal-2026-reassessing,
    title = "Reassessing Extractive {QA} Datasets at Scale: {LLM}-as-a-Judge and In-Depth Analyses",
    author = "Ho, Xanh  and
      Huang, Jiahao  and
      Boudin, Florian  and
      Aizawa, Akiko",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.9/",
    pages = "84--101",
    ISBN = "979-8-89176-423-1"
}