发表机构
Department of Computer and Information Science, University of Pennsylvania（宾夕法尼亚大学计算机与信息科学系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
EviStreams是一个开源无代码平台，通过结构化字段定义和盲法双审裁决，让医学系统综述的AI数据提取符合协议且可复现，评估显示字段规范比模型选择更影响质量。
AI 中文摘要
系统综述是临床指南的基础，但其数据提取步骤是受协议化工作流程约束的主要专家劳动瓶颈：两名评审员独立提取每项研究，一名裁决者解决分歧，团队保留每项价值如何产生的可审计记录。大型语言模型可以辅助提取，但这种辅助必须符合既定的综述协议并保持可复现性。我们提出了EviStreams，一个实时、开源、无代码的Web平台，让综述团队在三个关键阶段控制AI辅助提取：程序设计（在任何代码运行前批准的结构化分解）、字段规范（根据试点校准的类型化字段定义）和提取预测（评审员盲法双重评审与裁决）。通过表单构建器，领域专家定义类型化字段而非提示词，对上传的PDF运行提取，检查每个值及其来源的支持段落，并将评审员盲法双重评审解析为可审计的共识导出。对四个临床语料库和三个前沿模型系列进行的评估（随系统发布）表明，提取质量受字段规范的影响远大于模型选择。EviStreams已在https://evistreams.com/demo上线，并以Apache-2.0许可证发布。
英文摘要
Systematic reviews underpin clinical guidelines, yet their data-extraction step is a major expert-labor bottleneck bound by a protocolized workflow: two reviewers extract each study independently, an adjudicator resolves disagreements, and the team keeps an auditable record of how every value was produced. Large language models can assist with extraction, but that assistance must fit established review protocols and preserve reproducibility. We present EviStreams, a live, open-source, no-code web platform that puts review teams in control of AI-assisted extraction at three key stages: program design (a structured decomposition approved before any code runs), field specification (typed field definitions calibrated from a pilot), and extracted predictions (reviewer-blinded dual review with adjudication). Working through a form builder, a domain expert defines typed fields rather than prompts, runs extraction over uploaded PDFs, inspects every value alongside the supporting passage it came from, and resolves a reviewer-blinded dual review into an auditable consensus export. An evaluation across four clinical corpora and three frontier model families, released with the system, shows that extraction quality is shaped far more by the field specification than by the choice of model. EviStreams is live at https://evistreams.com/demo and released under Apache-2.0.
Comments12 pages, 5 figures. Accepted to EMNLP 2026 System Demonstrations
