LLM-based System for Technical Writing Real-time Review in Urban Construction and Technology
Open accessAbstract
This pilot study addresses the critical challenge of providing timely and comprehensive feedback on technical reports in Architectural, Engineering, and Construction (AEC) education. The significance of effective writing skills in the AEC industry is paramount for technical reports. Traditional methods of evaluation and feedback are time-consuming, leading to a deficiency in students' exposure to writing practice and hindering their holistic skill development. This study introduces a Large Language Model (LLM)-based System for Real-time Technical Writing Review in AEC, aiming to assess the reliability of LLMs in offering constructive feedback and grading for technical reports, focusing on Construction Capstone Projects. The proposed system aligns with pedagogical frameworks, such as Writing Across the Curriculum and AI Across the Curriculum, generative learning theory, and the Feedback Model. This model is applied Construction Capstone Project at the University of Florida, focusing on targeted writing assignments. Preliminary results indicate the model's ability to evaluate sustainability aspects of projects, providing detailed criteria-based feedback. This pilot study aims to lay the groundwork for an AI-assisted system tailored for AEC education, offering real-time, personalized feedback to enhance students' writing skills. The findings hold implications for researchers, students, and educators seeking innovative solutions to address the challenges in technical writing education within AEC.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
GPT-4 exhibited gaps in construction-specific terminology and standards.
“the domainspecific knowledge of the model which exhibited gaps in construction-specific terminology and standards”
From A review of LLMs and their applications in the architecture, engineering and construction industry (2025) · cites this paper as Castro et al. (2024)
The Results (page unavailable) show that GPT-4 ranked some projects differently from human graders because it emphasized the number of sustainability measures rather than how well the reports supported LEED certification. This supports a narrower concern about applying a construction-related standard, but the paper does not report gaps in construction-specific terminology. The Conclusions (page unavailable) also say GPT-4 selected evaluation categories matching current sustainability criteria. (LLM, conf=0.82)
Experimental — accuracy not yet measuredGPT-4 identified relevant sustainability criteria for student projects but prioritized quantity of sustainability measures over quality and depth of explanations.
“GPT-4 is able to identify relevant sustainability criteria for each student project but tended to prioritize the quantity of sustainability measures over the quality and depth of explanations.”
From A review of LLMs and their applications in the architecture, engineering and construction industry (2025) · cites this paper as Castro et al. (2024)
GPT-4 had difficulties with reports containing multiple figures and tables.
“GPT-4 encountered issues with the format, exhibiting difficulties in reports with multiple figures and tables.”
From A review of LLMs and their applications in the architecture, engineering and construction industry (2025) · cites this paper as Castro et al. (2024)
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Southworth, J., Migliaccio, K., Glover, J., Glover, J., Reed, D., McCarty, C., Brendemuhl, J., & Thomas, A. (2023) · Computers and Education: Artificial Intelligence · doi:10.1016/j.caeai.2023.100127 · Cited by 647 · cited 1× · see citing works
“Complementary, AI Across the Curriculum encompasses all AI applications and aligns with the interdisciplinary character of WAC for imparting AI knowledge and skills to the upcoming generation (Southworth et al., 2023).”
BackgroundPromoting Student Metacognition
Tanner, K. D. (2012) · CBE—Life Sciences Education · doi:10.1187/cbe.12-03-0033 · Cited by 618 · see citing works
What makes for effective feedback: staff and student perspectives
Dawson, P., Henderson, M., Mahoney, P., Phillips, M., Ryan, T., Boud, D., & Molloy, E. (2019) · Assessment & Evaluation in Higher Education · doi:10.1080/02602938.2018.1467877 · Cited by 514 · see citing works
Jeong, H., & Hmelo‐Silver, C. E. (2016) · Educational Psychologist · doi:10.1080/00461520.2016.1158654 · Cited by 476 · see citing works
Stevens, D. D., & Levi, A. J. (2004) · Cited by 469 · see citing works
Using large language models in psychology
Demszky, D., Yang, D., Yeager, D. S., Bryan, C. J., Clapper, M., Chandhok, S., Eichstaedt, J. C., Hecht, C., Jamieson, J., Johnson, M., et al. (2023) · Nature Reviews Psychology · doi:10.1038/s44159-023-00241-5 · Cited by 369 · see citing works
What We Know, What We Still Need to Know: Teaching Adolescents to Write
Graham, S., & Perin, D. (2007) · Scientific Studies of Reading · doi:10.1080/10888430701530664 · Cited by 210 · see citing works
Looking Back as We Look Forward: Historicizing Writing Assessment
Yancey, K. B. (1999) · College Composition and Communication · doi:10.2307/358862 · Cited by 193 · see citing works
Writing across the Curriculum: A Guide to Developing Programs
Shamoon, L. K., McLeod, S. H., & Soven, M. K. (1993) · Modern Language Journal · doi:10.2307/329111 · Cited by 172 · see citing works
A Comparison of Practitioner and Student Writing in Civil Engineering
Conrad, S. (2017) · Journal of Engineering Education · doi:10.1002/jee.20161 · Cited by 150 · see citing works
Moore, M. G. (2002) · American Journal of Distance Education · doi:10.1207/s15389286ajde1602_1 · Cited by 81 · see citing works
The Architect's Handbook of Professional Practice
Gutman, R. (1992) · Journal of Architectural Education · doi:10.1080/10464883.1992.10734498 · Cited by 75 · see citing works
Lachner, A., Burkhart, C., & Nückles, M. (2017) · Computers in Human Behavior · doi:10.1016/j.chb.2017.03.008 · Cited by 47 · see citing works
Yoritomo, J. Y., Turnipseed, N., Cooper, S., Elliott, C. M., Gallagher, J., Popovics, J. S., Prior, P. A., & Zilles, J. L. (2020) · ASEE Annual Conference & Exposition · doi:10.18260/1-2--30467 · Cited by 26 · see citing works
Stakeholder Dynamics: Rethinking Roles and Responsibilities in User-Pay Transport PPP Projects
Castelblanco, G., & Guevara, J. (2024) · Journal of Construction Engineering and Management · doi:10.1061/jcemd4.coeng-14477 · Cited by 26 · see citing works
Self-citationPreparing Students for Writing in Civil Engineering Practice
Conrad, S., Pfeiffer, T., & Szymoniak, T. (2020) · ASEE Annual Conference & Exposition · doi:10.18260/1-2--21817 · Cited by 17 · see citing works
Castelblanco, G., Guevara, J., Mangano, G., & Rafele, C. (2024) · Construction Management and Economics · doi:10.1080/01446193.2024.2335566 · Cited by 17 · see citing works
Self-citationMediated-efficacy: Hope for “helpless” writers
Camfield, E. K. (2016) · Scholarly Commons (University of the Pacific) · Cited by 16 · see citing works
The Engineers’ Guide to Technical Writing: Insights for Budding Engineers
Khan, A. W. (2019) · Advances in Language and Literary Studies · doi:10.7575/aiac.alls.v.10n.4p.80 · Cited by 6 · see citing works
How to Write Technical Reports
Hering, H. (2018) · Springer eBooks · doi:10.1007/978-3-662-58107-0 · Cited by 5 · see citing works
Educational Opportunities for Technical Writing in Engineering Education
Ely, S., & Chen, J. (2024) · ASEE Annual Conference & Exposition · doi:10.18260/1-2--37004 · Cited by 2 · see citing works
Assessing The Need For Technical Writing Skills Among Construction Science Graduates
Choudhury, I., Rocha, R. E., & Burt, R. (2021) · doi:10.18260/1-2-620-38479 · Cited by 1 · see citing works
Flagged first, then by citations
1 of the 23 references couldn’t be matched to a known paper.
Research works printed but not linked: 2
- [12]12. Hattie, J., Timperley, H. (2007). The power of feedback. Review of educational research, 77(1), 81- 112.
- [24]24. Yao, M. Z., Ling, R. (2020). What is computer-mediated communication?. Journal of Computer- Mediated Communication. 25(1):4-8.
Cited by
Sorted by citations
A review of LLMs and their applications in the architecture, engineering and construction industry
Kampelopoulos, D., Tsanousa, A., Vrochidis, S., & Kompatsiaris, I. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11241-7 · Cited by 69 · see citing works
The sociolinguistic foundations of language modeling
Grieve, J., Bartl, S., Fuoli, M., Grafmiller, J., Huang, W., Jawerbaum, A., Murakami, A., Perlman, M., Rœmling, D., & Winter, B. (2025) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1472411 · Cited by 45 · see citing works
The impact of large language models on computer science student writing
Zdravkova, K., & Ilijoski, B. (2025) · International Journal of Educational Technology in Higher Education · doi:10.1186/s41239-025-00525-1 · Cited by 23 · see citing works
Performance of a Large‐Language Model in scoring construction management capstone design projects
Castelblanco, G., Castro, L. M. C., & Yang, Z. (2024) · Computer Applications in Engineering Education · doi:10.1002/cae.22796 · Cited by 22 · see citing works
Self-citationProposed Framework for LLM-Based Feedback in LEED Assignments
Yang, Z., Castelblanco, G., Castro, L. M. C., & Multani, M. K. (2025) · CIB Conferences · doi:10.7771/3067-4883.2036
Self-citationDevelopment of FeedCap: A Tool for Real-Time Writing Feedback in Capstone Design Projects
Yang, Z., Castelblanco, G., & Castro, L. M. C. (2025) · ASEE Annual Conference & Exposition · doi:10.18260/1-2--56288
Self-citationSrivastava, A., Jain, S., & Maity, R. (2026) · Advances in chemical pollution, environmental management and protection · doi:10.1016/bs.apmp.2025.11.004
Generación de reportes descriptivos usando inteligencia artificial generativa: Un mapeo sistemático
Ordóñez-Erazo, H. A., Luna, R. M. R., & Figueroa, J. R. (2026) · Ingeniería y Competitividad · doi:10.25100/iyc.v28i2.15700
A modular tool-driven RAG framework for engineering test documentation
Trappey, A. J. C., Huang, W.-Y., & Chien, C.-H. (2026) · Journal of Engineering Design · doi:10.1080/09544828.2026.2698389
AI-Enhanced Static Code Analyzer for Secure Coding Support
Jie, H. J., Mansor, M., & Singh, R. (2026) · Malaysian Journal of Science and Advanced Technology · doi:10.56532/mjsat.v6i3.729
- Authors
- Cruz Castro, L. M., Castelblanco, G., & Antonenko, P. D.
- Affiliations
- University of Florida (US)
- Venue
- EPiC Series in Built Environment
- Publisher
- EasyChair
- Published
- 2024-05-26
- Volume
- 5
- Pages
- 130-120
- ISSN
- 2632-881X (ISSN-L)
- OpenAlex
- W4399031574
- Semantic Scholar
- 0d912e9c5242b44bcbab549c8337e7ea83bead13
- Cited by
- 8
- References
- 23
- Citations by year
- 2026: 3 · 2025: 4 · 2024: 1
- FWCI
- 3.04
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- EPiC series in built environment (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Information Systems › Artificial Intelligence in Education
- Social Sciences › Education › Student Assessment and Feedback
- Physical Sciences › Computer Science › Artificial Intelligence › Educational Technology and Pedagogy
- Keywords
- large language models, technical writing, real-time feedback, AEC education, automated grading, AI-assisted writing instruction, writing across the curriculum, feedback model, sustainability assessment
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
