@inproceedings{kim-etal-2024-team,
    title = "{TEAM} {MIPAL} at {MEDIQA}-{M}3{G} 2024: Large {VQA} Models for Dermatological Diagnosis",
    author = "Kim, Hyeonjin  and
      Kim, Min  and
      Jang, Jae  and
      Yoo, KiYoon  and
      Kwak, Nojun",
    editor = "Naumann, Tristan  and
      Ben Abacha, Asma  and
      Bethard, Steven  and
      Roberts, Kirk  and
      Bitterman, Danielle",
    booktitle = "Proceedings of the 6th Clinical Natural Language Processing Workshop",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.clinicalnlp-1.30/",
    doi = "10.18653/v1/2024.clinicalnlp-1.30",
    pages = "334--338",
    abstract = "This paper describes the methods used for the NAACL 2024 workshop MEDIQA-M3G shared task for generating medical answers from image and query data for skin diseases. MedVInT-Decoder, LLaVA, and LLaVA-Med are chosen as base models. Finetuned with the task dataset on the dermatological domain, MedVInT-Decoder achieved a BLEU score of 3.82 during competition, while LLaVA and LLaVA-Med reached 6.98 and 4.62 afterward, respectively."
}