重新思考科学建模：迈向物理一致且可模拟执行的程序化生成
Rethinking Scientific Modeling: Toward Physically Consistent and Simulation-Executable Programmatic Generation
AI总结：
针对大型语言模型在工程建模中生成代码的物理不一致问题，提出结合领域知识构建、约束对齐和验证驱动的框架，并引入CivilInstruct数据集和MBEval基准，通过两阶段微调提升模型生成的可执行性和物理一致性。
摘要：
结构建模是计算工程科学的基础组成部分，其中即使是微小的物理不一致或规范违反也可能使下游模拟失效。大型语言模型（LLMs）在自动生成建模代码方面的潜力已被证实。然而，在严格的工程约束下，不可执行或物理不一致的输出仍然普遍存在。因此，提出了一种物理一致自动建筑建模框架，整合了领域知识构建、面向约束的模型对齐和验证驱动的评估。引入了CivilInstruct作为领域特定数据集，形式化了结构工程知识和约束推理，以实现可模拟的模型生成。进一步采用两阶段微调策略来强制约束满足和应用程序编程接口合规性，显著减少了幻觉和不一致输出。提出了MBEval作为验证驱动的基准，通过闭环验证评估可执行性和结构动力学一致性。实验结果表明，在严格的验证指标上，该方法相比基线持续改进。我们的代码可在 https://github.com/Jovanqing/AutoBM 获取。
英文摘要：
Structural modeling is a fundamental component of computational engineering science, in which even minor physical inconsistencies or specification violations may invalidate downstream simulations. The potential of large language models (LLMs) for automatic generation of modeling code has been demonstrated. However, non-executable or physically inconsistent outputs remain prevalent under stringent engineering constraints. A framework for physics-consistent automatic building modeling is therefore proposed, integrating domain knowledge construction, constraint-oriented model alignment, and verification-driven evaluation. CivilInstruct is introduced as a domain-specific dataset that formalizes structural engineering knowledge and constraint reasoning to enable simulation-ready model generation. A two-stage fine-tuning strategy is further employed to enforce constraint satisfaction and application programming interface compliance, substantially reducing hallucinated and non-conforming outputs. MBEval is presented as a verification-driven benchmark that evaluates executability and structural dynamics consistency through closed-loop validation. Experimental results show consistent improvements over baselines across rigorous verification metrics. Our code is available at https://github.com/Jovanqing/AutoBM.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
