Trained students use more diverse higher-order prompting strategies, including generating new questions absent among controls¶
Claim · All claims
Evidence · 1 study · causalr2·q3
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.
q3 i? The experimental group's frequency of higher-order strategies (comparisons/summaries, definitions, insight-seeking, question generation) consistently exceeded controls; 14.0% of trained students used generating new questions versus 0.0% of controls. → Huang 2026
Evidence¶
Huang 2026¶
Huang, B., Xie, L., Liu, Y., Liu, X., Tang, H., Feng, X., Qiao, C., Guo, Q., Wu, C., & Bao, L. (2026). From answer machine to collaborative partner: impact of structured generative AI training on scientific problem solving in STEM education. International Journal of STEM Education. https://doi.org/10.1186/s40594-026-00652-9
q3 · i? · causal · r2
Qualitative content analysis of chat logs coded by two researchers (Krippendorff's α = 0.951) across six strategy types. Both groups relied heavily on image-only prompting (82.2% vs. 88.0% of students); trained students showed higher participation in higher-order strategies.
"the proportion of students engaging in the obtaining insight into problems strategy more than doubled, increasing from 20.0% (9 students) in the control group to 42.0% (21 students) in the experimental group. Notably, 14.0% (7 students) of the trained participants progressed to the generating new questions strategy for self-assessment, a higher-order behavior entirely absent among control-group students (0.0%)"
Discussion¶
Related Claims¶
- 75% of student-authored physics questions met combined high-quality criteria (clear, correct, plausible distractors, above recall, adequate explanation) — the general claim this finding bears on, with the studies behind it
- Questioning Strategies Improve Learning — a broader claim this one bears on
- Critical questions support competency-based science assessment by evaluating higher-order thinking, knowledge transfer and reasoning patterns beyond fact memorization — related
- Self-questioning improves comprehension — related
- Pre-written prompts increase Justifications and Alternative ideas in children's pair-programming talk and shift the role of Simple questions — related
- SSRL-directed question prompts enhanced individual participation in collaborative problem-solving, and socioemotional interaction diversity related to regulation contributions (reported findings) — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
trained-students-higher-order-prompting-strategies |
title |
Trained students use more diverse higher-order prompting strategies, including generating new questions absent among controls |
description |
Trained students use more diverse higher-order prompting strategies, including generating new questions absent among controls |
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 — huang-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.