用合成数据训练模型自动检测医疗文本错误，效果接近真人医生。
MedVAL: Toward Expert-Level Medical Text Validation with Language Models
- 用自监督方法生成虚假医学文本，训练模型判断输出是否与输入一致。
- 在6类真实医疗任务中，模型准确率从66%提升至83%，显著优于人类专家基准。
- 无需医生标注，可让大模型在无参考的情况下自我校验，适合临床部署。
随着语言模型在临床环境中的广泛应用，评估其生成的医疗文本准确性与安全性变得紧迫。当前依赖人工医生评审，但成本高且缺乏专家参考输出。尽管‘大模型作为裁判’模式具备可扩展性，前沿模型仍可能遗漏细微但关键的临床错误。本文提出MedVAL，一种新颖的自监督、数据高效蒸馏方法，利用合成数据训练评估模型，无需医生标签或参考输出即可判断生成内容是否与输入事实一致。为评估性能，我们构建了MedVAL-Bench，包含840个医生标注的输出，涵盖6种多样化的医疗任务。在10个先进语言模型（包括开源与专有模型）上测试，MedVAL蒸馏使与医生判断的一致性显著提升（p < 0.001），平均F1得分从66%升至83%。即使在表现最佳的专有模型GPT-4o上，也提升了8%且未使用医生标注数据，其表现统计上不劣于多名医生共同标注的基准（p < 0.001）。为推动可扩展、风险可控的临床集成，我们开源：1）代码库（https://github.com/StanfordMIMI/MedVAL），2）MedVAL-Bench数据集（https://huggingface.co/datasets/stanfordmimi/MedVAL-Bench），3）MedVAL-4B模型（https://huggingface.co/stanfordmimi/MedVAL-4B）。该基准表明，大模型已接近专家级医疗文本验证能力。
原文摘要 · Abstract (English)
With the growing use of language models (LMs) in clinical environments, there is an immediate need to evaluate the accuracy and safety of LM-generated medical text. Currently, such evaluation relies solely on manual physician review. However, detecting errors in LM-generated text is challenging because 1) manual review is costly and 2) expert-composed reference outputs are often unavailable in real-world settings. While the "LLM-as-a-judge" paradigm offers scalable evaluation, even frontier LMs can miss subtle but clinically significant errors. We propose MedVAL, a novel, self-supervised, data-efficient distillation method that leverages synthetic data to train evaluator LMs to assess whether LM-generated medical outputs are factually consistent with inputs, without requiring physician labels or reference outputs. To evaluate LM performance, we introduce MedVAL-Bench, a dataset of 840 physician-annotated outputs across 6 diverse medical tasks capturing real-world challenges. Across 10 state-of-the-art LMs spanning open-source and proprietary models, MedVAL distillation significantly improves (p < 0.001) alignment with physicians across seen and unseen tasks, increasing average F1 scores from 66% to 83%. Despite strong baseline performance, MedVAL improves the best-performing proprietary LM (GPT-4o) by 8% without training on physician-labeled data, demonstrating a performance statistically non-inferior to a single human expert on a subset annotated by multiple physicians (p < 0.001). To support a scalable, risk-aware pathway towards clinical integration, we open-source: 1) Codebase (https://github.com/StanfordMIMI/MedVAL), 2) MedVAL-Bench (https://huggingface.co/datasets/stanfordmimi/MedVAL-Bench), 3) MedVAL-4B (https://huggingface.co/stanfordmimi/MedVAL-4B). Our benchmark provides evidence of LMs approaching expert-level ability in validating AI-generated medical text.
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。