MoBayes：一种用于对话式临床决策支持中推理与语言分离的模块化贝叶斯框架
MoBayes: A Modular Bayesian Framework for Separating Reasoning from Language in Conversational Clinical Decision Support
AI总结：
提出MoBayes框架，通过将LLM作为语言接口、贝叶斯模块进行概率推理，实现推理与语言分离，在临床决策支持中优于独立前沿LLM医生。
摘要：
大型语言模型（LLM）越来越多地用于对话式临床决策支持，但它们将下一个标记预测与概率决策混为一谈。我们认为这种混淆反映了架构上的局限性：此类系统缺乏显式的后验追踪、可控的弃权阈值和可审计的推理链。我们引入MoBayes，一个模块化贝叶斯对话框架，将推理与语言分离。LLM仅作为语言接口，将患者对话解析为结构化观察，而贝叶斯模块对这些观察进行概率推理以更新后验，通过期望信息增益选择后续问题，并通过校准的决策阈值决定何时停止或推迟。这种设计实现了显式后验追踪、可控的选择性决策，以及无需重新训练语言模型即可替换的特定人群统计后端。在经验知识和LLM生成的知识库上，MoBayes优于独立的前沿LLM医生，包括匹配模型系列的比较，其中廉价的传感器模型与MoBayes配对以较低成本超过更大的自主模型。在对抗性患者沟通风格和不同诊断场景下，该优势依然存在。这些结果表明，可靠的对话式临床决策支持系统应将概率推理与语言生成分离，而不是仅扩大模型规模。代码可在https://anonymous.4open.science/r/MoBayes/获取。
英文摘要：
Large language models (LLMs) are increasingly used for conversational clinical decision support, yet they conflate next token prediction with probabilistic decision making. We argue that this conflation reflects an architectural limitation: such systems lack explicit posterior tracking, controllable abstention thresholds, and auditable reasoning chains. We introduce MoBayes, a Modular Bayesian dialogue framework that separates reasoning from language. The LLM acts only as a language interface, parsing patient conversation into structured observations, while a Bayesian module performs probabilistic inference over these observations to update posteriors, select follow-up questions via expected-information-gain and determine when to stop or defer through calibrated decision thresholds. This design enables explicit posterior tracking, controllable selective decision-making, and replaceable population-specific statistical backends without retraining the language model. Across empirical and LLM-generated knowledge bases, MoBayes outperforms standalone frontier LLM doctors, including matched model-family comparisons where inexpensive sensor models paired with MoBayes exceed larger autonomous models at lower cost. The advantage persists under adversarial patient communication styles and across varying diagnostic scenarios. These results suggest that reliable conversational clinical decision support systems should separate probabilistic reasoning from language generation rather than scaling model size alone. Code is available at https://anonymous.4open.science/r/MoBayes/
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
