GenAI feedback quality correlates with initial essay quality while teacher feedback quality does not¶

Claim · All claims
Evidence · 1 study (3 entries) · causal r2 · q3 · i2–i3
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly

Subclaims¶

Reading the evidence codes

q is the design tier, i the impact, n the sample, and the kind with its r the rigour judged within that kind: what each code means.

This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.

q3 i3 Zero-shot GenAI feedback quality showed a moderate significant correlation with initial essay quality (r = 0.53). → Farrokhnia 2026 q3 i3 CoT GenAI feedback quality also correlated significantly with initial essay quality (r = 0.42), though more weakly than Zero-shot. → Farrokhnia 2026 (2) q3 i2 Teacher feedback quality showed a weak, statistically non-significant correlation with initial essay quality (r = 0.21). → Farrokhnia 2026 (3)

Evidence¶

Farrokhnia 2026¶

Farrokhnia, M., Latifi, S., Papadopoulos, P. M., Hogenkamp, L., Gijlers, H., Khosravi, H., & Noroozi, O. (2026). Generative AI offers more, but students revise less: comparing the effects of teacher and AI feedback on student essay revisions. International Journal of Educational Technology in Higher Education. https://doi.org/10.1186/s41239-026-00579-9

q3 · i3 · causal · r2

Pearson bivariate correlation analysis for RQ2 in the Zero-shot condition (n = 24) found a moderate significant association between feedback quality and initial essay quality, "indicating a significant reliance on the quality of the initial essays".

"A moderate correlation was shown between GenAI feedback generated using Zero-shot prompt and initial essay quality (r = 0.53, p < .01), indicating a significant reliance on the quality of the initial essays for generating feedback."

Farrokhnia 2026 (2)¶

q3 · i3 · causal · r2

Pearson correlation for the CoT condition (n = 22) showed a moderate significant association (r = 0.42), weaker than in the Zero-shot condition, suggesting somewhat less dependence on initial draft quality.

"Similarly, a moderate correlation was observed between GenAI feedback generated using a CoT prompt and initial essay quality (r = 0.42, p < .05), though this correlation was weaker compared to the Zero-shot prompt condition"

Farrokhnia 2026 (3)¶

q3 · i2 · causal · r2

Pearson correlation for the teacher condition (n = 24) found a weak, non-significant association (r = 0.21, p > .05), suggesting teacher feedback quality is less dependent on initial essay quality.

"a weak and statistically non-significant correlation between teacher feedback and initial essay quality ( r = 0.21, p > .05), suggesting that the quality of teacher feedback is less dependent on the initial quality of essays"

Discussion¶

Page metadata

Field	Value
`type`	`claim`
`id`	`genai-feedback-quality-tracks-initial-essay-quality`
`title`	`GenAI feedback quality correlates with initial essay quality while teacher feedback quality does not`
`description`	`GenAI feedback quality correlates with initial essay quality while teacher feedback quality does not`
`status`	`review`
`evidence_strength`	`moderate`
`newest_evidence`	`2026`
`recheck_by`	`2029`
`generated`	by `process:wiki-ingest` on `2026-10-10`
`trust`	unverified — no one has confirmed this page's content
`sources`	3 — `farrokhnia-2026`, `farrokhnia-2026-2`, `farrokhnia-2026-3`

Frontmatter is the page's machine-readable record — see the Schema & Guide.