A post-search study found no significant difference in item difficulty between AI- and human-generated MCQs, but higher discriminatory power for human questions¶
Claim · All claims
Evidence · 1 study · reviewr2·q1
Currency · newest study 2024 · not yet checked against its sources · not reviewed by a person · recheck by 2027: tool and model accuracy changes quickly
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.
q1 i? The review cites Laupichler et al. as finding no statistically significant difficulty difference between AI- and human-generated MCQs, while human questions had significantly higher discriminatory power. → Artsi Yaara 2024
Evidence¶
Artsi Yaara 2024¶
Artsi Yaara, Sorin Vera, Konen Eli, Glicksberg Benjamin S., Nadkarni Girish, Klang Eyal. (2024). Large language models for generating medical examinations: systematic review. BMC Medical Education. https://doi.org/10.1186/s12909-024-05239-y
q1 · i? · review · r2
Second-hand citation: the review reports this result from a paper by Laupichler et al. published after its search period, comparing student performance in answering AI versus human generated MCQs. The review's account is accepted as attributed; the underlying study was not read.
"They found no statistically significant difference in item difficulty between AI generated MCQs and human generated questions, but discriminatory power was statistically significantly higher in humans than LLM questions"
Discussion¶
Related Claims¶
Page metadata
| Field | Value |
|---|---|
status |
review |
generated |
by process:wiki-ingest on 2026-10-31 |
trust |
unverified — no one has confirmed this page's content |
Frontmatter is the page's machine-readable record — see the Schema & Guide.