用大模型生成精神科报告，兼顾真实、多样与隐私安全。
Fidelity, Diversity, and Privacy: A Multi-Dimensional LLM Evaluation for Clinical Data Augmentation
- 用ICD-10编码控制生成精神科评估报告，提升临床相关性。
- 三维度评估显示各模型生成文本兼具语义真实、词汇多样与隐私安全。
- 适合需要合规合成数据的医疗NLP研究者使用。
精神健康领域高质量标注数据稀缺，且隐私法规限制数据共享，制约了机器学习模型训练。本文利用大语言模型（LLM）构建数据增强流程，采用DeepSeek-R1、OpenBioLLM-Llama3和Qwen 3.5，在特定国际疾病分类第十版（ICD-10）编码条件下生成合成精神健康评估报告。为避免模式崩溃或隐私泄露（如记忆化），提出多维度评估框架，从语义保真度、词汇多样性及隐私/抄袭风险三个层面评估生成文本。结果表明，所有模型均能生成临床合理、内容丰富且隐私安全的合成报告，显著扩充可用于临床自然语言处理任务的训练数据，同时保障患者隐私。
原文摘要 · Abstract (English)
The scarcity of high-quality annotated medical data, particularly in mental health, poses a significant bottleneck for training robust machine learning models. Privacy regulations restrict data sharing, making synthetic data generation a promising alternative. The use of Large Language Models (LLMs) in a data augmentation pipeline could be leveraged as an alternative in this field. In the proposed methodology, DeepSeek-R1, OpenBioLLM-Llama3 and Qwen 3.5 are used to generate synthetic mental health evaluation reports conditioned on specific International Classification of Diseases, Tenth Revision (ICD-10) codes. Because naive text generation can lead to mode collapse or privacy breaches (memorization), a comprehensive evaluation framework is introduced. The generated diagnostic texts are assessed across three dimensions: semantic fidelity, lexical diversity, and privacy/plagiarism. The results demonstrate that all models can generate clinically coherent, diverse, and privacy-safe synthetic reports, significantly expanding the available training data for clinical natural language processing tasks without compromising patient confidentiality.
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。