Large language models for automated grading in geotechnics

Purpose The purpose of this study is to explore the application of automated grading systems in geotechnics using large language models (LLMs) and cosine similarity for enhanced assessment and educational content generation. By training and testing LLMs on synthetic and real student data, the study seeks to develop robust systems for grading technical reports and open-ended questions, aligned with industry standards. Additionally, it aims to enhance student learning through auto-grading, immediate feedback and content generation, while addressing ethical considerations such as data privacy and fairness. Ultimately, the study strives to demonstrate the potential of LLMs to improve consistency, efficiency and educational outcomes. Design/methodology/approach The study employs a mixed-methods approach to develop and validate automated grading systems in geotechnics. Initially, correct answers were generated manually and synthetically using a generative pre-trained transformer model, with synthetic answers compared to correct ones via cosine similarity. Real student answers underwent similar evaluation. A Web-based tool was created to assess responses in real-time, providing dynamic feedback. Additionally, LLMs were fine-tuned on geotechnics textbooks and validated using synthetic and real student data. Anonymized student project reports were graded automatically, showcasing the potential and limitations of LLMs in consistent grading and educational content generation. Ethical considerations were addressed throughout. Findings The study demonstrated the potential of LLMs in geotechnics education by developing ML-driven systems for grading and content generation. The grading system, using cosine similarity and LLMs, provided consistent and objective assessments comparable to human graders. Immediate feedback on open-ended questions enhanced learning outcomes, enabling students to address knowledge gaps effectively. Fine-tuning LLMs with geotechnics textbooks and industry standards facilitated the generation of accurate, relevant questions and answers, further improved by retrieval-augmented generation (RAG). Data augmentation techniques enhanced model robustness, while ethical considerations, including data privacy, fairness, and transparency, ensured responsible deployment and fostered trust among stakeholders. Originality/value This study offers originality and value by pioneering the application of LLMs and cosine similarity for automated grading in geotechnics education, a domain with limited exploration in educational technology. By integrating RAG and fine-tuning LLMs with domain-specific textbooks, it bridges the gap between advanced machine learning techniques and practical applications in engineering education. The development of real-time feedback tools and robust grading systems enhances both student learning and instructional efficiency. Furthermore, addressing ethical considerations such as fairness and data privacy sets a precedent for responsible artificial intelligence (AI) deployment, contributing to the broader adoption of AI in academia.