Prompted, unprompted, and slide-based learning conditions yield statistically comparable multiple-choice performance¶

Claim · All claims
Evidence · 1 study · causal r2 · q3
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q3 i? Multiple-choice accuracy did not differ significantly across the three conditions (F = 2.38, p = 0.099), though the prompted group's descriptive mean was highest. → Xiaoyu Hou 2026

Evidence¶

Xiaoyu Hou 2026¶

Xiaoyu Hou, Bo Xiao, Hexu Liu and Shane Mueller. (2026). The Role of Instructional Guidance in Generative AI-Assisted Learning: Empirical Evidence from Construction Engineering Education. https://arxiv.org/abs/2606.05509 doi:10.48550/arxiv.2606.05509

q3 · i? · causal · r2

Same randomized controlled experiment (n = 95). Multiple-choice accuracy means were 0.63, 0.59, and 0.72 for control, unprompted, and prompted groups; the between-condition ANOVA on total MC score was "not statistically significant (F = 2.38, p = 0.099 )". Equivalence was not tested.

"For multiple-choice questions, the Prompted group achieves the highest mean score (6.45), followed by the NA (5.67) and Unprompted (5.27) groups. However, the ANOVA results indicate that this difference is not statistically significant (F = 2.38, p = 0.099 )."

Discussion¶

Related Claims¶

• Scaffolding improves learning — the general claim this finding bears on, with the studies behind it
• Prompted AI-supported learning raises overall post-test scores above both slide-based and unprompted AI conditions — reports the opposite
• Theory-guided five-step prompting of AI interaction improves open-ended explanation performance in construction education review, while unprompted AI access alone does not — related
• Structured prompting raises perceived interaction clarity and dependability but reduces perceived novelty of AI-supported learning — related
• MCQ accuracy was high (above 87%) across all conditions with no significant difference between diverse and generic explanations — related
• Students reported similar perceived information quantity across conditions, indicating diverse explanations did not produce perceived information overload — related