@inproceedings{lim-etal-2025-format,
    title = "Format Inertia: A Failure Mechanism of {LLM}s in Medical Pre-Consultation",
    author = "Lim, Seungseop  and
      Kim, Gibaeg  and
      Han, Wooseok  and
      Seo, Jean  and
      Lee, Hyunkyung  and
      Yoo, Jaehyo  and
      Yang, Eunho",
    editor = "Potdar, Saloni  and
      Rojas-Barahona, Lina  and
      Montella, Sebastien",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = nov,
    year = "2025",
    address = "Suzhou (China)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-industry.101/",
    pages = "1437--1450",
    ISBN = "979-8-89176-333-3",
    abstract = "Recent advances in Large Language Models (LLMs) have brought significant improvements to various service domains, including chatbots and medical pre-consultation applications. In the healthcare domain, the most common approach for adapting LLMs to multi-turn dialogue generation is Supervised Fine-Tuning (SFT). However, datasets for SFT in tasks like medical pre-consultation typically exhibit a skewed turn-count distribution. Training on such data induces a novel failure mechanism we term **Format Inertia**, where models tend to generate repetitive, format-correct, but diagnostically uninformative questions in long medical dialogues. To mitigate this observed failure mechanism, we adopt a simple, data-centric method that rebalances the turn-count distribution of the training dataset. Experimental results show that our approach substantially alleviates Format Inertia in medical pre-consultation."
}