LLM在医患对话中因数据分布偏斜，易产生重复无效提问。
Format Inertia: A Failure Mechanism of LLMs in Medical Pre-Consultation
- 通过重平衡训练数据的对话轮次分布来缓解问题
- 显著减少长对话中重复、无诊断价值的提问
- 适合医疗对话系统优化与数据工程研究者
大语言模型在医疗预问诊等多轮对话任务中广泛应用，主流方法为监督微调（SFT）。然而，医疗问诊数据集普遍存在轮次分布不均的问题。在此类数据上训练会引发一种新型失效机制——格式惯性：模型生成看似符合格式、重复冗余，但缺乏诊断信息的提问。本文提出一种以数据为中心的简单方法，通过重平衡训练数据的轮次分布来缓解该问题。实验表明，该方法能显著减轻医疗预问诊场景下的格式惯性现象。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。