cs.CL提交于 2026-10-23已译

从结构化记录到患者叙事：保持 LLM 生成健康摘要的临床一致性

From Structured Records to Patient Narratives: Preserving Clinical Alignment in LLM-Generated Health Summaries

Bayram Ayadi · Florian Geissler · Johanna Schmidhuber

中文摘要

随着可穿戴设备与数字健康系统持续生成纵向生理记录，如何用患者易懂的文字表达这些观察，仍是显著挑战。大语言模型(LLM)可将结构化临床信息转为可读叙事，但简化过程可能造成临床精确含义的语义漂移。研究针对经期健康监测，采用结合结构化证据条件控制与检索增强生成(RAG)的提示式约束生成框架，开展循证健康摘要。评估包括自然语言推理(NLI)、原子事实性与可读性。对3种 LLM 生成的4,500份摘要进行实验后，显式依据约束持续提升临床一致性，尤其改善不确定性保留；当依据检索到的证据评估忠实性时，忠实性总体得以保持或提高，而遗漏情况因模型而异。更高的临床一致性也会增加阅读难度和医学术语使用。

关键要点

01结构化临床信息转为患者叙事时，可能出现语义漂移
02以经期健康监测为场景，结合结构化证据条件与 RAG
03通过 NLI、原子事实性和可读性评估 4,500 份摘要
04显式依据约束改善不确定性保留及临床一致性
05临床一致性提升伴随阅读难度与医学术语增加

解读

尚无解读。

原始英文摘要

arXiv:2610.31467v1 Announce Type: new Abstract: As wearable and digital health systems increasingly generate longitudinal physiological records, communicating these observations in patient-accessible language remains a significant challenge. Large Language Models (LLMs) offer a promising mechanism for translating structured clinical information into readable narratives, but this process may introduce semantic drift, where clinically precise meaning is distorted during simplification. We investigate evidence-grounded health summarization for menstrual health monitoring using a constrained generation framework that combines structured evidence conditioning with Retrieval-Augmented Generation (RAG) using a prompt-based constrained generation framework. We evaluate semantic alignment using Natural Language Inference (NLI), atomic factuality metrics, and readability measures. Across three LLMs and 4,500 generated summaries, explicit grounding constraints consistently improve clinical alignment, particularly by improving uncertainty preservation and, once faithfulness is evaluated against retrieved evidence, generally preserving or improving faithfulness, while effects on omission remain model-dependent. We also find that improved clinical alignment comes at the cost of increased reading difficulty and medical terminology. These findings highlight the need to jointly evaluate faithfulness, uncertainty preservation, and readability when developing patient-facing medical LLM systems.