Children's plan quality improves substantially after receiving LLM-generated adaptive feedback¶
Claim · All claims
Evidence · 1 study · causalr3·q3·i3large
Currency · newest study 2026 · 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.
q3 i3 Plan quality scores were significantly higher after LLM-generated adaptive feedback than before, with a large effect size (r = .86). → Sukjaitham 2026
Evidence¶
Sukjaitham 2026¶
Sukjaitham, S., Schaaf, M., Brod, G., & Breitwieser, J. (2026). Adaptivity Makes Feedback Effective: Evidence From AI-Generated Feedback on Children's Plans. Preprint. https://osf.io/4w6rz/overview?view_only=dd3ec8d2878243579a463ccd0d77d723 doi:10.31234/osf.io/t2eac_v1
q3 · i3 · causal · r3
Preregistered within-subjects experiment with 155 children (Mage = 12.08 years) completing six planning trials. A Wilcoxon signed-rank test comparing pre- and post-support plans in the LLM condition found a significant increase, "a large effect size (r = .86)".
"Results from the nonparametric Wilcoxon signed -rank test showed that plan quality scores were significantly higher after receiving LLM-generated adaptive feedback than before feedback (V = 10,440, p < .001). This improvement was associated with a large effect size (r = .86)"
Discussion¶
Related Claims¶
- Plan quality improves more after LLM-generated adaptive feedback than after high-quality generic guidance — related
- Children perceive LLM-generated adaptive feedback as more helpful and more motivating than generic guidance — related
- Trial-level perceived usefulness of feedback is associated with the magnitude of plan quality improvement — related
- Children's self-efficacy for planning did not significantly moderate plan quality improvements after feedback — related
- LLM feedback receives higher expert ratings on six of seven quality dimensions, with tone the exception — related
- Students show large immediate pre-to-post knowledge gains within a single LLM-supported learning session — related
- Students' argumentative essay quality improves substantially from initial to revised drafts regardless of feedback source — related
- Test-takers rate LLM-generated feedback as persuasive and useful as human instructor feedback (Wilcoxon signed-rank tests show no significant difference) — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
plan-quality-improves-after-llm-adaptive-feedback |
title |
Children's plan quality improves substantially after receiving LLM-generated adaptive feedback |
description |
Children's plan quality improves substantially after receiving LLM-generated adaptive feedback |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2026 |
source_checked |
2026-10-20 |
generated |
by process:wiki-ingest on 2026-10-12 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — sukjaitham-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.