Test-takers rate LLM-generated feedback as persuasive and useful as human instructor feedback (Wilcoxon signed-rank tests show no significant difference)¶
Claim · All claims
Evidence · 1 study · designr2·q3
Currency · newest study 2026 · not yet checked against its sources · 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.
q3 i? Average persuasiveness scores for Q1–Q3 were high (3.67–4.05) for both human and ChatGPT feedback with no significant difference; usefulness scores were slightly lower (2.95–3.54) with no significant difference. → Satoshi Takahashi 2026
Evidence¶
Satoshi Takahashi 2026¶
Satoshi Takahashi, Atsushi Yoshikawa, Megumi Kose, Kenichi Suzuki, Chieko Inoue, Yumi Watanabe, and Mari Sawada. (2026). Automating Constructive Assessment with Large Language Models: Toward Scalable and Repeated Evaluation of Practical Competence. arXiv. https://arxiv.org/abs/2609.25790 doi:10.48550/arxiv.2609.25790
q3 · i? · design · r2
Experiment 3: 80 respondents rated blinded human and ChatGPT feedback on 5-point Likert scales for persuasiveness and usefulness; 74 participants with no missing data were analyzed, and Wilcoxon signed-rank tests found no significant differences.
"The average persuasiveness scores for Q1–Q3 were high (3.67–4.05) for both human and ChatGPT feedback, with no significant difference according to the Wilcoxon signed-rank test."
Discussion¶
Related Claims¶
- AI literacy warnings reduce LLM political persuasion by roughly one-half (meta-analytic -48.1%) — related
- In Study 2, both general and specific warnings at least marginally reduce attitude change, with no significant difference between them — related
- In Study 1, the general warning significantly reduced persuasive effects on housing-policy attitudes (b=−1.81, p= 0.001) — related
- Children's plan quality improves substantially after receiving LLM-generated adaptive feedback — related
- Students preferred AI-generated personalized videos over human-recorded non-personalized videos in direct comparison — related
- Children perceive LLM-generated adaptive feedback as more helpful and more motivating than generic guidance — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
llm-feedback-rated-equal-to-human-feedback |
title |
Test-takers rate LLM-generated feedback as persuasive and useful as human instructor feedback (Wilcoxon signed-rank tests show no significant difference) |
description |
Test-takers rate LLM-generated feedback as persuasive and useful as human instructor feedback (Wilcoxon signed-rank tests show no significant difference) |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2026 |
generated |
by process:wiki-ingest on 2026-10-10 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — satoshi-takahashi-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.