Students rated the LLM-based assignments as useful, challenging, engaging, and enjoyable at both the first and fifth iterations, with no significant change across the semester¶

Claim · All claims
Evidence · 1 study (2 entries) · causal r1 · q2
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? After the first iteration, ratings of usefulness, challenge, engagement, and enjoyment were all significantly above the neutral midpoint. → Daniel M. Oppenheimer 2025 q2 i? Ratings remained significantly positive after the fifth iteration and none of the metrics significantly changed from first to fifth. → Daniel M. Oppenheimer 2025 (2)

Evidence¶

Daniel M. Oppenheimer 2025¶

Daniel M. Oppenheimer, Trent N. Cash, Allison E. Connell Pensky. (2025). You've Got AI Friend in Me: LLMs as Collaborative Learning Partners. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-025-00521-6

q2 · i? · causal · r1

Self-reported ratings on −5 to 5 bi-valenced Likert scales after the first assignment: useful (x̄ = 2.32), challenging (x̄ = 1.42), engaging (x̄ = 2.51), enjoyable (x̄ = 2.03). All significantly above the midpoint of 0; no effect size printed.

"one-sample t-tests comparing these numbers to the neutral midpoint of 0 were run and revealed that they were all highly significant (ts(79) > 7.84, ps < 0.001)."

Daniel M. Oppenheimer 2025 (2)¶

Daniel M. Oppenheimer, Trent N. Cash, Allison E. Connell Pensky. (2025). You've Got AI Friend in Me: LLMs as Collaborative Learning Partners. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-025-00521-6

q2 · i? · causal · r1

After the fifth assignment, ratings remained positive: useful (x̄ = 2.48), challenging (x̄ = 0.63), engaging (x̄ = 2.22), enjoyable (x̄ = 1.81). The article reports "None of these metrics significantly changed from the first to fifth iteration of the assignment."

"The one-sample t-test comparing these numbers to the neutral midpoint of 0 revealed that these were also highly significant (ts(96) > 3.06, ps < 0.002)."

Discussion¶

Learner Variables¶

• Interest — outcome: instruction changes it

Related Claims¶

• Students in a scaffolded LLM-collaboration course improved significantly on initial argument quality, prompt engineering, and response to AI feedback from the first to the fifth assignment — related
• Students' self-efficacy for using generative AI increased over the semester, with current self-efficacy significantly higher after the fifth assignment than after the first — related
• Student chatbot queries were overwhelmingly task-oriented initial inquiries, dominated by definition requests and pasted assignment questions rather than iterative critique — related
• Midterm self-efficacy (comfort and confidence) did not differ between conditions after three assignments, though both varied significantly across algorithmic topics — related