Newest papers

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

Bayram Ayadi, Florian Geißler, Johanna Schmidhuber · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31467 · cited by 0 works (OpenAlex) · open-access PDF

Indonesian

Sebagai sistem kesehatan digital dan portabel semakin menghasilkan catatan fisiologis longitudinal, berkomunikasi pengamatan ini dalam bahasa yang dapat diakses pasien tetap menjadi tantangan yang signifikan. Model Bahasa Besar (LLM) menawarkan mekanisme yang menjanjikan untuk menerjemahkan informasi klinis terstruktur ke dalam narasi yang dapat dibaca, tetapi proses ini dapat memperkenalkan drift semantik, di mana makna yang akurat secara klinis terganggu selama simplifikasi. Kami menyelidiki summarization kesehatan berbasis bukti untuk pemantauan kesehatan menstruasi menggunakan kerangka kerja generasi terbatas yang menggabungkan kondisi bukti terstruktur dengan Retrieval-Augmented Generation (RAG) menggunakan kerangka kerja generasi terbatas yang didasarkan pada prompt. Kami mengevaluasi penyesuaian semantik menggunakan Natural Language Inference (NLI), metrik fakta atomik, dan pengukuran

Machine translation (Meta M2M100); the English original follows.

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.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Readability, Automatic summarization, Computer science, Unified Medical Language System, Natural language generation, Natural language processing

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange