LLM-based System for Technical Writing Real-time Review in Urban Construction and Technology

Abstract

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.