@inproceedings{fu-etal-2023-large,
    title = "Are Large Language Models Reliable Judges? A Study on the Factuality Evaluation Capabilities of {LLM}s",
    author = "Fu, Xue-Yong  and
      Laskar, Md Tahmid Rahman  and
      Chen, Cheng  and
      Tn, Shashi Bhushan",
    editor = "Gehrmann, Sebastian  and
      Wang, Alex  and
      Sedoc, Jo{\~a}o  and
      Clark, Elizabeth  and
      Dhole, Kaustubh  and
      Chandu, Khyathi Raghavi  and
      Santus, Enrico  and
      Sedghamiz, Hooman",
    booktitle = "Proceedings of the Third Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2023.gem-1.25/",
    pages = "310--316"
}