No reliable moderation of depth effects by baseline knowledge, though simple slopes suggest an exploratory pattern¶
Claim · All claims
Evidence · 1 study · associationalr1·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? No Pre × Depth interaction reached conventional significance for task quality, post-test, or gain outcomes (all p > .11). → Vangelis Tsiligkiris 2026
Evidence¶
Vangelis Tsiligkiris 2026¶
Vangelis Tsiligkiris. (2026). What students ask matters: LLM interaction depth, task quality, and immediate recall in higher education. International Journal of Educational Technology in Higher Education. https://doi.org/10.1186/s41239-026-00617-6
q2 · i? · associational · r1
Moderation analysis adding Pre × Depth interaction terms to task-quality, post-test, and gain models for 22 students. The article states these patterns "should be interpreted as exploratory and require replication" given the small sample.
"No interaction reached conventional significance (all p > .11). Simple-slopes probing suggested a pattern in which the estimated Depth effect on task quality was larger at lower baseline knowledge (Pre = −1 SD: β = 9.58, p = .050) than at the mean (β = 4.75, p = .104), and it was negligible at higher baseline knowledge (Pre = +1 SD: β = 0.00, p = .989)."
Discussion¶
Related Claims¶
- Interaction depth is not associated with immediate recall or gains once baseline knowledge is controlled — related
- Explanation-seeking interaction depth is positively associated with task quality beyond baseline knowledge and volume — related
- Exploratory, non-significant pattern suggests students with stronger learner profiles may show larger AI-assisted exam gains — related
- AI Interaction Competence, not GPA or prior knowledge, is the decisive moderator of LLM-assisted learning gains — related
- In replication analyses, the variety conditions were particularly beneficial for students with low prior GPAs, while the same-type-only conditions had negligible effect sizes — related
- Prior mathematical competence by spatial ability (MRT) interaction was only a trend, with competence slopes strongest in the high-MRT group — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
no-reliable-moderation-baseline-knowledge |
title |
No reliable moderation of depth effects by baseline knowledge, though simple slopes suggest an exploratory pattern |
description |
No reliable moderation of depth effects by baseline knowledge, though simple slopes suggest an exploratory pattern |
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 — vangelis-tsiligkiris-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.