通过一致性驱动的迭代优化实现自然语言到SysMLv2的翻译
Natural-Language to SysMLv2 Translation via Conformance-Driven Iterative Refinement
浏览论文内容
中文总结 AI 辅助
研究自然语言到SysMLv2的翻译，提出由一致性检查器驱动的框架，在生成-检查-修复循环中嵌入检查器，以生产级接受为终止条件，经评估，该方法相比单次生成大幅提高了生产一致性。
中文摘要 AI 辅助
基于模型的系统工程（MBSE）依赖形式化系统模型作为系统生命周期中表示需求、结构和行为的主要技术工件。随着SysMLv2作为文本语言的标准化，将自然语言描述直接翻译成可执行模型的兴趣日益增加。对于实际部署，生成的模型必须被工业建模环境接受，而不仅仅是满足语法约束。我们提出了一个由一致性检查器驱动的框架，用于可靠的自然语言到SysMLv2的翻译，该框架将生产级接受作为终止条件。该系统在生成-检查-修复循环中嵌入了一个SysMLv2一致性检查器。每个模型都使用检查器进行评估，并将确定性诊断纳入修订，直到实现零一致性错误。使用生产检查器作为预言机可确保该框架以可部署性而非语法合理性为目标。我们在四个大语言模型后端的151个提示的完整SysMBench提示集上评估了该方法，产生了604个提示-模型案例。单次生成实现了51.16%的生产一致性接受，而我们的方法实现了100.00%的一致性。通过将生产一致性从后处理检查提升为生成过程中的控制机制，该框架将概率性输出转换为适合加载、可视化和工程使用的生产可接受的SysMLv2工件。
英文摘要
Model-Based Systems Engineering (MBSE) relies on formal system models as primary technical artifacts for representing requirements, structure, and behavior across the system lifecycle. With the standardization of SysMLv2 as a textual language, interest is increasing in translating natural-language descriptions directly into executable models. For practical deployment, generated models must be accepted by industrial modeling environments, not merely satisfy grammar constraints. We present a conformance-checker-driven framework for reliable natural-language-to-SysMLv2 translation that enforces production-level acceptance as the termination condition. The system embeds a SysMLv2 conformance checker within a generate-check-repair loop. Each model is evaluated using the checker, and deterministic diagnostics are incorporated into revisions until zero conformance errors are achieved. Using the production checker as the oracle ensures the framework targets deployability rather than grammar plausibility. We evaluate the approach on the full SysMBench prompt set of 151 prompts across four large language model backends, yielding 604 prompt-model cases. Single-shot generation achieves 51.16% production-conformance acceptance, while our approach achieves 100.00% conformance. By elevating production conformance from a post-processing check to a control mechanism within generation, the framework converts probabilistic outputs into production-accepted SysMLv2 artifacts suitable for loading, visualization, and engineering use.
发表机构
- Carnegie Mellon University（卡内基梅隆大学）
- Virginia Tech（弗吉尼亚理工大学）
机构由 AI 辅助整理，请以论文原文为准。
