{"ID":2861316,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.01688","arxiv_id":"2510.01688","title":"Format Inertia: A Failure Mechanism of LLMs in Medical Pre-Consultation","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.","short_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,...","url_abs":"https://arxiv.org/abs/2510.01688","url_pdf":"https://arxiv.org/pdf/2510.01688v2","authors":"[\"Seungseop Lim\",\"Gibaeg Kim\",\"Wooseok Han\",\"Jean Seo\",\"Hyunkyung Lee\",\"Jaehyo Yoo\",\"Eunho Yang\"]","published":"2025-10-02T05:29:38Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}