2025 ASEE Annual Conference & Exposition

BOARD # 50: Evaluation of Current Generative AI Chatbots for Their Use in Structural Engineering Related Fields

Presented at Civil Engineering Division (CIVIL) Poster Session

The structural engineering community is currently determining how Artificial Intelligence (AI) can benefit our industry. While professional organizations, such as the National Council of Structural Engineering Associations (NCSEA), have developed task forces to investigate ways that AI may potentially accomplish this feat, there is limited research on what available AI technologies exist that could potentially provide professionals and students with accurate results regarding structural engineering topics. Additionally, it is our responsibility as educators to prepare our students for industry advancements and future trends. According to a news flash survey from Inside Higher Ed in 2024 of 1,250 college students across 49 four- and two-year colleges, nearly 75% of students say their institutions should at least somewhat be preparing them for AI in the workplace. However, a 2024 survey of College and University Chief Academic Officers by Inside Higher Ed found that only 14 percent have reviewed the curriculum to ensure it will prepare students for AI in the workforce. Considering this information, what can we do as educators to ensure our students in fields related to structural engineering are prepared for AI in the workplace?

This paper will discuss the evaluation of current generative AI chatbots in their unmodified configurations for their use in fields related to structural engineering. Various generative AI chatbots, including ChatGPT, Claude, Gemini, CoPilot, and SE GPT will be asked the same questions related to the field of structural engineering. An in-depth discussion on the methodology of question selection is provided. The accuracy of their responses, which is determined as accurate, mixed accuracy, and inaccurate based on criteria presented in the paper will be used to evaluate each generative AI chatbot to determine if existing generative AI chatbots can be used to answer questions related to structural engineering. The information gathered from this paper can be used by educators to understand the differences in current generative AI chatbots, their limitations, and provide students with a similar understanding so they can be introduced to this technology and be prepared to use it upon graduation.

Authors
  1. Alex Campbell Oklahoma State University [biography]
  2. Prof. John J Phillips P.E. Oklahoma State University [biography]
Note

The full paper will be available to logged in and registered conference attendees once the conference starts on June 22, 2025, and to all visitors after the conference ends on June 25, 2025