Jiazi Hu

Bo Yuan, Jiazi Hu

Course evaluation is a critical component in higher education pedagogy. It not only serves to identify limitations in existing course designs and provide a basis for curricular innovation, but also to offer quantitative insights for university administrative decision-making. Traditional evaluation methods, primarily comprising student surveys, instructor self-assessments, and expert reviews, often encounter challenges, including inherent subjectivity, feedback delays, inefficiencies, and limitations in addressing innovative teaching approaches. Recent advancements in large language models (LLMs) within artificial intelligence (AI) present promising new avenues for enhancing course evaluation processes. This study explores the application of LLMs in automated course evaluation from multiple perspectives and conducts rigorous experiments across 100 courses at a major university in China. The findings indicate that: (1) LLMs can be an effective tool for course evaluation; (2) their effectiveness is contingent upon appropriate fine-tuning and prompt engineering; and (3) LLM-generated evaluation results demonstrate a notable level of rationality and interpretability.

Bo Yuan, Jiazi Hu

While Large Language Models (LLMs) are increasingly envisioned as intelligent assistants for personalized learning, systematic head-to-head evaluations in authentic learning scenarios remain scarce. This study presents an empirical comparison of three state-of-the-art LLMs on a tutoring task simulating a realistic learning setting. Using a dataset containing a student's responses to ten mixed-format questions with correctness labels, each model was asked to (i) analyze the quiz to identify underlying knowledge components, (ii) infer the student's mastery profile, and (iii) generate targeted guidance for improvement. To mitigate subjectivity and evaluator bias, Gemini was employed as a virtual judge to perform pairwise comparisons across multiple dimensions: accuracy, clarity, actionability, and appropriateness. Results analyzed via the Bradley-Terry model reveal that GPT-4o is generally preferred, producing feedback that is more informative and better structured than its counterparts, whereas DeepSeek-V3 and GLM-4.5 demonstrate intermittent strengths but lower consistency. These findings highlight the feasibility of deploying LLMs as advanced teaching assistants for individualized support and provide methodological insights for subsequent empirical research on LLM-driven personalized learning.

Bo Yuan, Jiazi Hu

Over the past decade, higher education has evolved through three distinct paradigms: the emergence of Massive Open Online Courses (MOOCs), the integration of Smart Teaching technologies into classrooms, and the rise of AI-enhanced learning. Each paradigm is intended to address specific challenges in traditional education: MOOCs enable ubiquitous access to learning resources; Smart Teaching supports real-time interaction with data-driven insights; and generative AI offers personalized feedback and on-demand content generation. However, these paradigms are often implemented in isolation due to their disparate technological origins and policy-driven adoption. This paper examines the origins, strengths, and limitations of each paradigm, and advocates a unified pedagogical perspective that synthesizes their complementary affordances. We propose a three-layer instructional framework that combines the scalability of MOOCs, the responsiveness of Smart Teaching, and the adaptivity of AI. To demonstrate its feasibility, we present a curriculum design for a project-based course. The findings highlight the framework's potential to enhance learner engagement, support instructors, and enable personalized yet scalable learning.