Perceived usefulness of response-level LLM feedback is most strongly associated with actionability and perceived accuracy¶

Claim · All claims
Evidence · 1 study · associational r1 · q3
Currency · newest study 2026 · checked against its sources 2026-10-20 (automated, 1 of 1 entry) · not reviewed by a person

Subclaims¶

q3 i? A standardised regression of perceived usefulness on the other four response-level dimensions accounted for 76% of variance, with actionability and accuracy the only coefficients whose bootstrap CIs excluded zero. → Mendonça PC 2026

Evidence¶

Mendonça PC 2026¶

Mendonça PC, Quintal F, Figueiredo M and Mendonça F (2026) Perceived usefulness and intention to use large language model-generated feedback across three educational levels: a user-centred study in programming. Front. Educ. 11:1934069. https://doi.org/10.3389/feduc.2026.1934069

q3 · i? · associational · r1

Standardised OLS regression on student-level ratings (n = 144) with Johnson's relative weights; the model accounted for 76% of variance [R2 = 0.76, F(4, 139) = 108.58, p < 0.001]. By relative weight, actionability accounted for 32.6% and accuracy for 29.0% of explained variance; "The standardised coefficients of accuracy [β = 0.35, 95% CI (0.16, 0.50)] and actionability [β = 0.43, 95% CI (0.18, 0.80)] had bootstrap CIs that excluded zero".

"The standardised coefficients of accuracy [β = 0.35, 95% CI (0.16, 0.50)] and actionability [β = 0.43, 95% CI (0.18, 0.80)] had bootstrap CIs that excluded zero"

Discussion¶

Related Claims¶

• Feedback Most Effective At Task And Process Levels — the general claim this finding bears on, with the studies behind it

• Feedback improves learning by a medium amount on average, but its effect varies widely with the information it carries, and a substantial share of feedback effects are negative — the general claim this finding bears on, with the studies behind it

• Intention to use consolidated LLM reports is associated with motivation and personalisation — related
• Students rate LLM-generated response-level feedback favourably, with clarity and perceived accuracy highest and actionability and usefulness lowest — related
• Feedback comprehension showed the strongest bivariate association with revision quality, and indirect associations through actionability and comprehension remained positive after adjustment — related
• Engagement-based metrics are more robust predictors of students' perceived feedback helpfulness than pedagogical dimensions — related
• Feedback Contemplators with High Emotional Strain perceived poorly structured feedback content—lacking depth, clarity, actionable information, and personalisation—as their biggest challenge in making sense of feedback — related