GPT-generated hints are moderately accessible by automated readability metrics (mean CAREC 0.128, mean CML2RI 3.95)¶
Claim · All claims
Evidence · 1 study · designr2·q2
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person · recheck by 2028: 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.
q2 i? CML2RI scores averaged 3.95 with most hints more cohesive than average. → Reddig 2025
Evidence¶
Reddig 2025¶
Reddig, J. M., Arora, A., & MacLellan, C. J. (2025). Generating In-Context, Personalized Feedback for Intelligent Tutors with Large Language Models. Int J Artif Intell Educ. https://doi.org/10.1007/s40593-025-00505-6
q2 · i? · design · r2
Coh-Metrix L2 Readability Index analysis of the same hints, where higher values indicate easier processing for second-language readers; high-scoring hints had strong lexical cohesion or familiar vocabulary.
"The histogram shows a slightly right-skewed distribution with an average at 3.95."
Discussion¶
Learner Variables¶
- Access — outcome: instruction changes it
Related Claims¶
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
gpt-hints-moderately-accessible-readability |
title |
GPT-generated hints are moderately accessible by automated readability metrics (mean CAREC 0.128, mean CML2RI 3.95) |
description |
GPT-generated hints are moderately accessible by automated readability metrics (mean CAREC 0.128, mean CML2RI 3.95) |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2025 |
recheck_by |
2028 |
generated |
by process:wiki-ingest on 2026-10-12 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — reddig-2025 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.