Students evaluate GenAI explanations for assumed background and audience, reading unfamiliar cultural references and excessive scaffolding as signals about who the explanation was written for¶
Claim · All claims
Evidence · 2 studies · 2 qualitativer3·q2
Currency · no dated study recorded · 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? Participants flagged explanations that assumed prior knowledge or domain familiarity (e.g., sports and gaming references) the student did not have. → assumed-background
q2 i? Some students read excessive explanation and repetition as condescending social signals of assumed low competence. → over-explanation
Evidence¶
assumed-background¶
Seth Bernstein and Naaz Sibia. 2026. Flawed but Memorable: Student Critical Reception of Interest-Personalized GenAI Analogies in Computing Education. Koli Calling '26. https://arxiv.org/abs/2609.06095 doi:10.48550/arxiv.2609.06095
q2 · i? · qualitative · r3
RQ2 findings from reflexive thematic analysis of the ten-participant study. The article reports "assumed domain familiarity, particularly around sports and gaming references," with P9 recalling sports analogies she could not use and P2 noting jargon assumptions even in a game he knew.
"A related failure was assumed domain familiarity, particularly around sports and gaming references."
over-explanation¶
Seth Bernstein and Naaz Sibia. 2026. Flawed but Memorable: Student Critical Reception of Interest-Personalized GenAI Analogies in Computing Education. Koli Calling '26. https://arxiv.org/abs/2609.06095
q2 · i? · qualitative · r3
The article reports that participants described excessive explanation as condescending; P9 said it felt like it was "trying to baby me," and P6 counted far too many words. Length and repetition were read as signals of assumed competence.
"This suggests students readlengthandrepetitionas social signals of assumed competence, not just as stylistic choices, complicating a simple "more scaffolding is safer" design heuristic."
Discussion¶
Related Claims¶
- Prior knowledge and trust calibration moderate GenAI learning effects: fluent output is most persuasive when learners least can challenge it — related
- Undergraduate computing students evaluate GenAI analogies by structural correspondence between source and target domain, flagging specific mapping breakdowns rather than judging holistically — related
- Most participants described interest-personalized GenAI analogies as more engaging or memorable than generic technical explanations — related
- Trust in personalized analogies moved in no single direction, while critical scrutiny tracked domain expertise more consistently than personal interest — related
- Students see obtaining explanations for their doubts as ChatGPT's most useful role in learning computer science — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
assumed-background-audience-signals |
title |
Students evaluate GenAI explanations for assumed background and audience, reading unfamiliar cultural references and excessive scaffolding as signals about who the explanation was written for |
description |
Students evaluate GenAI explanations for assumed background and audience, reading unfamiliar cultural references and excessive scaffolding as signals about who the explanation was written for |
status |
review |
evidence_strength |
weak |
generated |
by process:wiki-ingest on 2026-10-11 |
trust |
unverified — no one has confirmed this page's content |
sources |
2 — assumed-background, over-explanation |
Frontmatter is the page's machine-readable record — see the Schema & Guide.