arXiv 2604.062622026-04-07q-bio.QMcs.AI

从暴露到内化：用于上下文临床推理的双流校准

From Exposure to Internalization: Dual-Stream Calibration for In-context Clinical Reasoning

Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology（香港科技大学电子与计算机工程系）；College of Management and Economics, Laboratory of Computation and Analytics of Complex Management Systems (CACMS), Tianjin University（天津大学管理与经济学部、复杂管理系统计算与分析实验室）；Department of Computer Science and Engineering, The Hong Kong University of Science and Technology（香港科技大学计算机科学与工程系）

Chuang Zhao, Hongke Zhao, Xiaofang Zhou, Xiaomeng Li

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出双流校准框架，通过协同对齐两个校准流实现深度内化，提升临床推理的上下文适应能力，验证表明其在三个任务中优于现有方法。

摘要：

上下文临床推理需要基于复杂异质临床记录的稳健推理。尽管最先进的微调、上下文学习（ICL）和检索增强生成（RAG）能暴露知识，但往往无法实现真正的上下文内化：在推理时动态调整模型内部表示以适应个体案例的细微差别。为此，我们提出双流校准（DSC），一种测试时间训练框架，超越表面知识暴露，在推理期间实现深度内化。DSC通过协同对齐两个校准流促进输入内化。不同于被动上下文暴露，语义校准流通过最小化熵来稳定生成轨迹，强制对核心证据进行反思，内化语义锚点。同时，结构校准流通过迭代元学习目标吸收潜在推断依赖性。通过在测试时间训练于专业支持集，该流使模型能够弥合外部证据与内部逻辑之间的差距，将碎片化数据综合为连贯响应。我们的方法将推理范式从被动注意力匹配转向对潜在推断空间的主动优化。在十三个临床数据集中验证，DSC在三个不同任务范式中均表现出色，持续超越从训练依赖模型到测试时间学习框架的最先进基线。

英文摘要：

Contextual clinical reasoning demands robust inference grounded in complex, heterogeneous clinical records. While state-of-the-art fine-tuning, in-context learning (ICL), and retrieval-augmented generation (RAG) enable knowledge exposure, they often fall short of genuine contextual internalization: dynamically adjusting a model's internal representations to the subtle nuances of individual cases at inference time. To address this, we propose Dual-Stream Calibration (DSC), a test-time training framework that transcends superficial knowledge exposure to achieve deep internalization during inference. DSC facilitates input internalization by synergistically aligning two calibration streams. Unlike passive context exposure, the Semantic Calibration Stream enforces a deliberative reflection on core evidence, internalizing semantic anchors by minimizing entropy to stabilize generative trajectories. Simultaneously, the Structural Calibration Stream assimilates latent inferential dependencies through an iterative meta-learning objective. By training on specialized support sets at test-time, this stream enables the model to bridge the gap between external evidence and internal logic, synthesizing fragmented data into a coherent response. Our approach shifts the reasoning paradigm from passive attention-based matching to an active refinement of the latent inferential space. Validated against thirteen clinical datasets, DSC demonstrates superiority across three distinct task paradigms, consistently outstripping state-of-the-art baselines ranging from training-dependent models to test-time learning frameworks.

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。