提出可信生成式AI在汽车工程中的流程级设计原则
Workflow-Level Design Principles for Trustworthy GenAI in Automotive System Engineering
- 分段分解提示+轻量NLP校验提升需求变更识别完整度
- 实现从需求变更到系统模型更新的端到端自动化
- 通过可追溯测试保障安全关键场景下的可靠性
大型语言模型在安全关键系统工程中的应用受限于可信性、可追溯性及与既有验证流程的契合度。本文提出面向可信生成式AI集成的工作流级设计原则，并在端到端汽车工程流水线中验证：从需求差异识别、SysML v2架构更新到重新测试。首先，证明单体提示（大爆炸式）会遗漏大规模规范中的关键变更，而采用分段分解、多样性采样及轻量NLP校验的方法显著提升完整性与正确性。随后，将需求变更传播至SysML v2模型，并通过编译与静态分析验证更新有效性。此外，通过显式映射规范变量至架构端口与状态，生成可追溯的回归测试用例，为安全关键汽车工程中的生成式AI应用提供实用保障。
原文摘要 · Abstract (English)
The adoption of large language models in safety-critical system engineering is constrained by trustworthiness, traceability, and alignment with established verification practices. We propose workflow-level design principles for trustworthy GenAI integration and demonstrate them in an end-to-end automotive pipeline, from requirement delta identification to SysML v2 architecture update and re-testing. First, we show that monolithic ("big-bang") prompting misses critical changes in large specifications, while section-wise decomposition with diversity sampling and lightweight NLP sanity checks improves completeness and correctness. Then, we propagate requirement deltas into SysML v2 models and validate updates via compilation and static analysis. Additionally, we ensure traceable regression testing by generating test cases through explicit mappings from specification variables to architectural ports and states, providing practical safeguards for GenAI used in safety-critical automotive engineering.
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。