Students' evaluative judgment of cGPT responses shifted from strict principle compliance toward contextual appropriateness¶
Claim · All claims
Evidence · 1 study · qualitativer2·q2
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.
q2 i? As students encountered diverse GPT outputs, they moved from rigid adherence to predefined design principles toward judging responses by contextual appropriateness and user utility, valuing responses that technically failed a principle if they offered unexpected insights. → Lo S 2026
Evidence¶
Lo S 2026¶
Lo S, Lea T, Mavromoustakos A, Joseph B, Yii M, Exintaris B, Karunaratne N, Pearson DL, Ritchie T, Yuriev E and Pyun J (2026) Co-creating custom GPTs: an autoethnographic study of undergraduate students as partners in generative AI innovation. Front. Educ. 11:1818781. https://doi.org/10.3389/feduc.2026.1818781
q2 · i? · qualitative · r2
Inductive thematic analysis of summer-scholarship SPAR logs. Students learned that responses that technically "failed" a principle could still be valued for unexpected insights; the article states "This diversity thus necessitated an evolving, nuanced view in response evaluation".
"This diversity thus necessitated an evolving, nuanced view in response evaluation"
Discussion¶
Related Claims¶
- Students reported that continued interaction with a cGPT improved its adherence to instructions — related
- Small edits to cGPT instructions and knowledge bases had unpredictable effects on GPT responses during iterative co-design — related
- Placement students reported enhanced agency and ownership from the open-ended cGPT co-creation project — related
- GPT responses reliably incorporated broad ideas from instructions but resisted precise control — related
- High-level feedback on reasoning and synthesis should remain a human responsibility for the foreseeable future — related
- Students' appropriation of class interaction practices was mediated by prior sociohistorical educational experiences — related
- RLHF rapidly shapes model outputs toward rater-endorsed norms, improving surface compliance while leaving principle-level generalization unresolved — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
evolving-evaluative-judgment-cgpt-responses |
title |
Students' evaluative judgment of cGPT responses shifted from strict principle compliance toward contextual appropriateness |
description |
Students' evaluative judgment of cGPT responses shifted from strict principle compliance toward contextual appropriateness |
status |
review |
evidence_strength |
weak |
newest_evidence |
2026 |
generated |
by process:wiki-ingest on 2026-10-11 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — lo-s-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.