Structured prompting raises perceived interaction clarity and dependability but reduces perceived novelty of AI-supported learning¶

Claim · All claims
Evidence · 1 study (2 entries) · causal r2 · q3
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q3 i? The prompted condition scored highest on pragmatic UEQ dimensions, particularly Perspicuity (1.59 vs 0.77 control) and Dependability (1.23). → Xiaoyu Hou 2026 q3 i? Novelty scores were lower in both AI conditions than in the slide-based control condition. → Xiaoyu Hou 2026 (2)

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

UEQ (short version, 26 items, six dimensions, −3 to +3 scale) administered to all 95 participants. The prompted group's Perspicuity mean of 1.59 versus the control's 0.77 was described as significantly enhancing clarity; Dependability was 1.23 versus 0.78.

"Perspicuity increases substantially in the Prompted group (1.59) compared to the Control group (0.77), indicating that the structured prompting strategy significantly enhances interaction clarity and reduces cognitive ambiguity."

Xiaoyu Hou 2026 (2)¶

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

q3 · i? · causal · r2

UEQ hedonic dimensions in the same experiment. The article reports Novelty "declines from 0.12 in the Control condition to −0.51 and −0.71 in the Prompted and Unprompted conditions, respectively", and Stimulation remained low across all conditions.

"Novelty declines from 0.12 in the Control condition to −0.51 and −0.71 in the Prompted and Unprompted conditions, respectively."

Discussion¶

Related Claims¶

• Prompted, unprompted, and slide-based learning conditions yield statistically comparable multiple-choice performance — related
• Prompted AI-supported learning raises overall post-test scores above both slide-based and unprompted AI conditions — related
• Pilot participants perceived AmicoMio and AmicoTuo as complementary modes serving different educational purposes rather than alternatives — related
• 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
• UEQ-S user-experience ratings were positive across tasks except one hedonic item on Task 1, with pragmatic qualities rated higher than hedonic — related
• Providing elaborate explanations and summary interactives instead of just scores increases students' perceptions of engagement and understanding and reduces mind wandering — related
• GAI-assisted DST creation produced significantly better team creativity performance than traditional methods, particularly in novelty and user experience — related
• Observable indicators showed micro-action completion was higher with structured task-clarity prompts and communicative autonomy improved particularly after AmicoTuo sessions, while transition-to-human follow-through was not quantified — related