This study explores the multifaceted factors influencing student learning motivations and educational outcomes. Utilizing a diverse student body from Franklin University Switzerland, the study emphasizes the impact of internal factors, such as the psychological state of flow and a self-reported love of learning, alongside GPA and student cohort influences like year of study, academic discipline, country of origin, and academic travel. Through a cross-sectional survey of 112 students, the study evaluates how these factors correlate with and diverge from each other and student GPAs, aiming to dissect the influences of intrinsic motivations, demographic variables, and educational experiences. Our analysis revealed significant correlations between students’ self-reported love of learning, experiences of flow, and academic performance. Conversely, academic travel did not show a significant direct impact, suggesting that while such experiences are enriching, they do not necessarily translate into a greater love of learning, flow, or higher academic achievement in the short term. However, demographic factors, particularly discipline of study and country of origin, significantly influenced the students’ love of learning, indicating varied motivational drives across different cultural and educational backgrounds. This study provides valuable insights for educational policymakers and institutions aiming to cultivate more engaging and fulfilling learning environments.

Educational assessment relies on well-constructed test items to measure student learning accurately, yet traditional item development is time-consuming and demands specialized psychometric expertise. Automatic item generation (AIG) offers template-based scalability, and recent large language model (LLM) advances promise to democratize item creation. However, fully automated approaches risk introducing factual errors, bias, and uneven difficulty. To address these challenges, we propose and evaluate a hybrid human-in-the-loop (HITL) framework for AIG that combines psychometric rigor with the linguistic flexibility of LLMs. In a Spring 2025 case study at Franklin University Switzerland, the instructor collaborated with ChatGPT (o4-mini-high) to generate parallel exam variants for two undergraduate business courses: Quantitative Reasoning and Data Mining. The instructor began by defining “radical” and “incidental” parameters to guide the model. Through iterative cycles of prompt, review, and refinement, the instructor validated content accuracy, calibrated difficulty, and mitigated bias. All interactions (including prompt templates, AI outputs, and human edits) were systematically documented, creating a transparent audit trail. Our findings demonstrate that a HITL approach to AIG can produce diverse, psychometrically equivalent exam forms with reduced development time, while preserving item validity and fairness, and potentially reducing cheating. This offers a replicable pathway for harnessing LLMs in educational measurement without sacrificing quality, equity, or accountability.