Students rated the usefulness of LLM-enhanced combined feedback significantly higher than their own prior expectations¶

Claim · All claims
Evidence · 1 study · causal r1 · q3
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q3 i? In the expectation/experience design, average ratings for feedback usefulness rose significantly from 3.11 (expectation) to 3.47 (experience), and for understanding learning progress from 3.01 to 3.89 (both paired t-tests significant). → Letteri 2025

Evidence¶

Letteri 2025¶

Letteri, I. & Vittorini, P. (2025). Enhancing Student Feedback in Data Science Education: Harnessing the Power of AI-Generated Approaches. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-025-00492-8

q3 · i? · causal · r1

Expectation/experience study with 136 students in AY 2023/24 using combined LLM feedback; paired t-tests on 5-point Likert ratings. The article reports the experience was "better than expected", with the increase "from 3.11 to 3.47 for the feedback usefulness".

"It shows that we measured an increase in the average ratings from 3.01 to 3.89 for understanding the learning progress and from 3.11 to 3.47 for the feedback usefulness. Both differences are statistically significant."

Discussion¶

Learner Variables¶

• Motivation — outcome: instruction changes it

Related Claims¶

• Adult learners expect AI to foster involvement by sparking questions, tapping interests, and providing continuous feedback and effort acknowledgment — related
• LLM-enhanced feedback did not yield a statistically significant improvement in final grades compared with traditional AI feedback — related