联邦学习让医院协作提取放射报告，不共享数据也能提升准确率。
FedPref: Federated Preference Learning for Structured Radiology Report Extraction
- 用冻结的公共语言模型生成候选结构化报告，本地标注排序后训练轻量适配器。
- 小医院在联邦协作下F1提升9.10点，整体平均提升2.49点，效果优于单独训练。
- 适合数据少、不能共享病历的医院，保护隐私同时提升诊断报告提取能力。
放射科报告以自由文本描述发现和位置，但下游检索与分析需要固定模式的结构化信息。标注数据在机构间分布不均：小型医院本地证据不足，而数据汇聚又可能不可行。我们提出FedPref：冻结的公共语言模型生成多个候选JSON提取结果，本地标注对这些结果进行排序，各机构协作训练轻量级Qwen3-8B适配器，仅交换模型更新。异构教师池提供跨模型对比，避免单一模型样本重复导致的退化。在六个模拟医院（数据量和疾病流行率不均）的开发集上，相比孤立训练，FedPref将客户端平均F1提升2.49点，最差站点提升9.10点，小数据站点增益最大。集中式训练联合偏好对数据集的客户端平均F1高出2.66点。在400份人工验证的封闭测试集上，FedPref得分为68.68 F1，集中训练为71.67，保持相同排序。因此，即使数据无法汇聚，机构也可通过协作受益于联邦学习，且从未共享报告或标注。
原文摘要 · Abstract (English)
Radiology reports describe findings and locations in free text, but downstream search and analysis require these relations in a fixed schema. Learning this extraction requires labels that are unevenly distributed across institutions: smaller hospitals have less local evidence, and pooling data may be infeasible. We introduce FedPref: frozen public language models propose alternative JSON extractions, local annotations rank them, and sites collaboratively train compact Qwen3-8B adapters while sharing only model updates. A heterogeneous teacher pool provides cross-model contrast when repeated single-model samples collapse. On development data from six simulated hospitals with unequal data volume and disease prevalence, FedPref improves client-mean F1 by 2.49 points and worst-site F1 by 9.10 points compared with training each site in isolation, with the largest gains at the sites holding the least data. Central training on the pooled preference-pair union is 2.66 points higher on client-mean F1. On a locked, 400-report manually validated gold test set, FedPref reaches 68.68 F1 and pooled training 71.67, preserving that same ordering. FedPref thus lets institutions with unequal, unpooled data benefit from collaboration without ever sharing reports or annotations.
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。