@inproceedings{jaumann-etal-2025-coling,
    title = "Coling-{U}ni{A} at {S}ci{VQA} 2025: Few-Shot Example Retrieval and Confidence-Informed Ensembling for Multimodal Large Language Models",
    author = "Jaumann, Christian  and
      Friedrich, Annemarie  and
      Lienhart, Rainer",
    editor = "Ghosal, Tirthankar  and
      Mayr, Philipp  and
      Singh, Amanpreet  and
      Naik, Aakanksha  and
      Rehm, Georg  and
      Freitag, Dayne  and
      Li, Dan  and
      Schimmler, Sonja  and
      De Waard, Anita",
    booktitle = "Proceedings of the Fifth Workshop on Scholarly Document Processing (SDP 2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.sdp-1.21/",
    doi = "10.18653/v1/2025.sdp-1.21",
    pages = "230--239",
    ISBN = "979-8-89176-265-7",
    abstract = "This paper describes our system for the SciVQA 2025 Shared Task on Scientific Visual Question Answering. Our system employs an ensemble of two Multimodal Large Language Models and various few-shot example retrieval strategies. The model and few-shot setting are selected based on the figure and question type. We also select answers based on the models' confidence levels. On the blind test data, our system ranks third out of seven with an average F1 score of 85.12 across ROUGE-1, ROUGE-L, and BERTS. Our code is publicly available."
}