aiqbench analysis
This empirical study demonstrates that unstructured interaction with generative AI offers no advantage over traditional slide-based learning, whereas a specific five-step prompting framework significantly improves performance on tasks requiring explanation and reasoning. The findings suggest that the pedagogical value of AI in education hinges on structured instructional guidance rather than mere access to the technology. For developers and educators, this highlights the necessity of embedding learning science principles directly into AI interaction designs to unlock deeper cognitive engagement.
The Role of Instructional Guidance in Generative AI-Assisted Learning: Empirical Evidence from Construction Engineering Education
arXiv:2606.05509v1 Announce Type: cross Abstract: Generative artificial intelligence (AI) is increasingly used to support self-directed learning, yet student interaction with such systems often remains unstructured, limiting engagement in deeper cognitive processes. This study examines how instructional guidance shapes student and AI interaction in construction education. A five-step prompting framework grounded in Generative Learning Theory (GLT) is introduced to guide learner interaction during review activities. A controlled experiment compares three learning conditions: slide-based learning, unprompted AI-supported learning, and prompted AI-supported learning. Learning performance is assessed using multiple-choice and open-ended tasks, and user experience is measured using the User Experience Questionnaire (UEQ). Performance differences are concentrated on tasks requiring explanation and reasoning. The prompted condition achieves higher open-ended scores, with an improvement of approximately 2 or 3 points on a scale of 18 (p < 0.01), while no significant differences are observed in multiple-choice performance. The unprompted condition remains comparable to slide-based learning. These findings indicate that the effectiveness of AI-supported learning depends on how interaction is structured. The proposed framework provides a basis for integrating learning science principles into generative AI systems for construction education.
Abstract:Generative artificial intelligence (AI) is increasingly used to support self-directed learning, yet student interaction with such systems often remains unstructured, limiting engagement in deeper cognitive processes. This study examines how instructional guidance shapes student and AI interaction in construction education. A five-step prompting framework grounded in Generative Learning Theory (GLT) is introduced to guide learner interaction during review activities. A controlled experiment compares three learning conditions: slide-based learning, unprompted AI-supported learning, and prompted AI-supported learning. Learning performance is assessed using multiple-choice and open-ended tasks, and user experience is measured using the User Experience Questionnaire (UEQ). Performance differences are concentrated on tasks requiring explanation and reasoning. The prompted condition achieves higher open-ended scores, with an improvement of approximately 2 or 3 points on a scale of 18 (p < 0.01), while no significant differences are observed in multiple-choice performance. The unprompted condition remains comparable to slide-based learning. These findings indicate that the effectiveness of AI-supported learning depends on how interaction is structured. The proposed framework provides a basis for integrating learning science principles into generative AI systems for construction education.
Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
arXiv:2606.05509 [cs.HC]
(or arXiv:2606.05509v1 [cs.HC] for this version)
https://doi.org/10.48550/arXiv.2606.05509 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 276 words
Related coverage
From Weak Task Specifications to Scientific Extraction Agents: Optimizing Task Construction
arXiv · Sep 30, 2026
Beyond English: Uncovering the Multilingual Gap in Vision-Language-Action Models
arXiv · Jun 17, 2026
CoFL-S: Spatially Queryable Sector Flow Fields for Local Language-Conditioned Navigation
arXiv · Sep 28, 2026
AgentHorizon: Evaluating Agentic Judges for Long-Horizon Computer-Use Tasks
arXiv · Oct 10, 2026