Toward Responsible AI in High-Stakes Domains: A Dataset for Building Static Analysis with LLMs in Structural Engineering

Carlos Avila (), Daniel Ilbay, Paola Tapia and David Rivera ()
Additional contact information
Carlos Avila: Grupo de Investigación de Energía, Minas y Agua (GIEMA), Facultad de Ciencias, Ingeniería y Construcción, Universidad UTE, Quito 170527, Ecuador
Daniel Ilbay: Facultad de Ciencias, Ingeniería y Construcción, Ingeniería Civil, Universidad UTE, Quito 170527, Ecuador
Paola Tapia: Facultad de Ciencias, Ingeniería y Construcción, Ingeniería Civil, Universidad UTE, Quito 170527, Ecuador
David Rivera: Facultad de Ciencias, Ingeniería y Construcción, Ingeniería Civil, Universidad UTE, Quito 170527, Ecuador

Data, 2025, vol. 10, issue 11, 1-12

Abstract: Modern engineering increasingly operates within socio-technical networks, such as the interdependence of energy grids, transport systems, and building codes, where decisions must be reliable and transparent. Large language models (LLMs) such as GPT promise efficiency by interpreting domain-specific queries and generating outputs, yet their predictive nature can introduce biases or fabricated values—risks that are unacceptable in structural engineering, where safety and compliance are paramount. This work presents a dataset that embeds generative AI into validated computational workflows through the Model Context Protocol (MCP). MCP enables API-based integration between ChatGPT (GPT-4o) and numerical solvers by converting natural-language prompts into structured solver commands. This creates context-aware exchanges—for example, transforming a query on seismic drift limits into an OpenSees analysis—whose results are benchmarked against manually generated ETABS models. This architecture ensures traceability, reproducibility, and alignment with seismic design standards. The dataset contains prompts, GPT outputs, solver-based analyses, and comparative error metrics for four reinforced concrete frame models designed under Ecuadorian (NEC-15) and U.S. (ASCE 7-22) codes. The end-to-end runtime for these scenarios, including LLM prompting, MCP orchestration, and solver execution, ranged between 6 and 12 s, demonstrating feasibility for design and verification workflows. Beyond providing records, the dataset establishes a reproducible methodology for integrating LLMs into engineering practice, with three goals: enabling independent verification, fostering collaboration across AI and civil engineering, and setting benchmarks for responsible AI use in high-stakes domains.

Keywords: generative AI-assisted structural analysis; model context protocol; human–machine interaction; computational efficiency; LLM–FEM integration (search for similar items in EconPapers)
JEL-codes: C8 C80 C81 C82 C83 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2306-5729/10/11/169/pdf (application/pdf)
https://www.mdpi.com/2306-5729/10/11/169/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jdataj:v:10:y:2025:i:11:p:169-:d:1778880

Access Statistics for this article

Data is currently edited by Ms. Becky Zhang

More articles in Data from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().