Students show large immediate pre-to-post knowledge gains within a single LLM-supported learning session¶
Claim · All claims
Evidence · 1 study · associationalr2·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? Postgraduate students' quiz scores improved substantially from pre-test to immediate post-test after an LLM-assisted task (Cohen's dz = 2.12, p < .001). → 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 · r2
Single-group pre-post study of 22 postgraduate business students in a 90-minute supervised session with a 10-minute pre-test, 60-minute LLM-assisted task, and 10-minute post-test. The paired t-test showed "a large improvement from pre- to post-test" with dz = 2.12; a Wilcoxon signed-rank test corroborated the pattern.
"A paired t-test showed a large improvement from pre- to post-test, t(21) = 9.93, p < .001, Cohen’s dz = 2.12 (95% CI [1.54, 2.70])."
Discussion¶
Related Claims¶
- Access to a generative-AI assistant raises task performance for both lower- and higher-education adults, with significantly larger gains for lower-education participants — related
- AI access raises immediate unaided test scores by 7.2 percentage points (0.28 SD) after a timed learning phase — related
- Post-test mathematics performance was significantly lower than pre-test after AI-tutor use — related
- Children's plan quality improves substantially after receiving LLM-generated adaptive feedback — related
- High school novices show large CT learning gains after using RoboBlockly Studio, improving Bebras performance from 1.28 to 2.88 of 4 tasks — related
- For within-subjects designs, the author recommends reporting Cohen's d_rm or Cohen's d_av rather than Cohen's dz — related
- AI-generated revision podcasts produce statistically significant immediate learning gains in medical students at both study centres — related
- In math problem solving, a tutor-plus-peers LLM arrangement produced the strongest unassisted post-task test accuracy, with accuracy increasing monotonically from Control to Tutor + Peers — related
- AI multimodal feedback produces post-test learning gains equivalent to educator feedback after controlling for pre-test performance — related
- In a randomised study with 40 CPR-naive lay adults in Tibet, 10 minutes of TibetCPR training produced rhythm-stabilisation gains that substantially exceeded unguided practice and transferred to an unscaffolded post-test — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
large-immediate-gains-llm-supported-session |
title |
Students show large immediate pre-to-post knowledge gains within a single LLM-supported learning session |
description |
Students show large immediate pre-to-post knowledge gains within a single LLM-supported learning session |
status |
review |
evidence_strength |
moderate |
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.