AI-generated (GPT-4) feedback produced no greater linguistic progress than human tutor feedback among ENL students over six weeks¶
Claim · All claims
Evidence · 1 study · causalr1·q2
Currency · newest study 2023 · checked against its sources 2026-10-20 (automated, 1 of 1 entry) · not reviewed by a person
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.
q2 i? In a six-week repeated-measures quasi-experiment with 48 ENL students, the group receiving GPT-4 feedback did not differ significantly from the human-tutor-feedback group in writing-score improvement. → Escalante 2023
Evidence¶
Escalante 2023¶
Escalante, J., Pack, A., & Barrett, A. (2023). AI-generated feedback on writing: insights into efficacy and ENL student preference. International Journal of Educational Technology in Higher Education, 20:57. https://doi.org/10.1186/s41239-023-00425-2
q2 · i? · causal · r1
Six-week repeated-measures quasi-experiment: experimental group (n = 23) received GPT-4 feedback, control group (n = 25) received human tutor feedback. The RM-ANOVA found "no significant interaction effect between group and time" (F = 3.094, p = 0.085, ηp2 = 0.063).
"The results of the mixed 2 × 2 RM-ANOVA analysis (Table 2) revealed there was no significant interaction effect between group and time (F = 3.094, p = 0.085, ηp2 = 0.063)"
Discussion¶
Related Claims¶
- ENL students were near-evenly split in preference between AI-generated and human tutor feedback — related
- Feedback source (human tutor vs GPT-4) had no significant effect on ENL students' posttest writing scores — possibly the same claim (merge candidate)
- Students who preferred human tutor feedback cited face-to-face interaction, engagement, follow-up questions, and speaking practice — related
- Teacher feedback produced larger first-task score gains that dropped 32.8% by the second task, while AI-assisted peer feedback gains remained stable (a learning-curve effect) — related
- Reviews citing one randomised trial (Bastani et al. 2025) report that unrestricted GPT-4 access in high-school mathematics raised assisted practice performance but left students worse off after withdrawal — related
- AI access raises immediate unaided test scores by 7.2 percentage points (0.28 SD) after a timed learning phase — related
- In a 16-week quasi-experiment, A-Level STEM students receiving high-frequency automated marking scored 16.8 percentage points higher on a blind-graded final mock exam than control students with human marking — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
gpt4-feedback-no-superior-linguistic-progress-enl |
title |
AI-generated (GPT-4) feedback produced no greater linguistic progress than human tutor feedback among ENL students over six weeks |
description |
AI-generated (GPT-4) feedback produced no greater linguistic progress than human tutor feedback among ENL students over six weeks |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2023 |
source_checked |
2026-10-20 |
generated |
by process:wiki-ingest on 2026-10-15 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — escalante-2023 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.