Distractor quality is the weakest automated dimension, with the lowest success rate (79.9%) and highest failure rate (15.6%)¶
Claim · All claims
Evidence · 1 study · designr2·q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person · recheck by 2029: 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.
q2 i? Distractor quality yielded the lowest success rate (79.9%) and the highest failure rate (15.6%), and distractor feedback quality showed a success rate of 86.1% with a 9.4% failure rate. → Xiaojing Duan 2026
Evidence¶
Xiaojing Duan 2026¶
Xiaojing Duan, Frederick Nwanganga, and Chaoli Wang. (2026). CODE-GEN: A Human-in-the-Loop RAG-Based Agentic AI System for Multiple-Choice Question Generation. https://arxiv.org/abs/2604.03926 doi:10.48550/arxiv.2604.03926
q2 · i? · design · r2
System-level quality analysis comparing the two pedagogical-judgment dimensions against the other five, with SME judgments as ground truth. The article reports "Distractor quality yielded the lowest success rate (79.9%)"; no effect size is printed.
"Distractor quality yielded the lowest success rate (79.9%) and the highest failure rate (15.6%), while distractor feedback quality showed a success rate of 86.1% with a comparatively elevated failure rate (9.4%)."
Discussion¶
Related Claims¶
- AI-generated assessment items frequently need faculty correction, supporting AI as a draft generator within quality assurance — the general claim this finding bears on, with the studies behind it
- Concept alignment achieves the highest success rate (98.6%) among the seven dimensions, attributed to the RAG-based design — related
- CODE-GEN achieves human-validated success rates of 79.9% to 98.6% across seven pedagogical evaluation dimensions — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
code-gen-distractor-quality-weakest-dimension |
title |
Distractor quality is the weakest automated dimension, with the lowest success rate (79.9%) and highest failure rate (15.6%) |
description |
Distractor quality is the weakest automated dimension, with the lowest success rate (79.9%) and highest failure rate (15.6%) |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2026 |
recheck_by |
2029 |
generated |
by process:wiki-ingest on 2026-10-10 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — xiaojing-duan-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.