面向连贯多图 SysML 模型的验证数据集与基准
原标题：A Validated Dataset and Benchmark for Coherent Multi-Diagram SysML Models
AI 摘要
该论文发布了 SEMAADB，一个包含 3000 个工程上下文和 15000 张 SysML 图的数据集与基准，每个上下文含需求、块定义、活动、状态机、序列五个相互关联的视图。作者对图集进行了一致性与渲染校验，并人工验证 100 个上下文作为测试集。评估三个语言模型在图表修复和跨图更新任务上的表现，结果显示语法修复已接近解决，但语义修复和跨图一致性仍是难题。
正文节选
A Validated Dataset and Benchmark for Coherent Multi-Diagram SysML Models Abstract Systems engineers use several diagrams to describe the structure and behavior of systems. Engineers create these diagrams together to make sure that they use the same elements and remain consistent with one another. Large language models can generate diagrams as text or code, which makes it possible to create system diagrams automatically. However, their ability to generate coherent sets of diagrams is not well un