AI Paper Atlas

Research map / Large language models / AI and society

Assessing the Quality of AI-Generated Exams: A Large-Scale Field Study

Calvin Isley, Joshua Gilbert, Evangelos Kassos, Michaela Kocher, Allen Nie, Emma Brunskill, Ben Domingue, Jake Hofman, Joscha Legewie, Teddy Svoronos, Charlotte Tuminelli, Sharad Goel

AAAI 2026 · Large language models › AI and society · approach: Critiques of LLM claims and judging · 9 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use AI-generated questions instead of AP Statistics questionsAI-generated exams · item difficultymean difficulty beta: 0.35 -> -0.45Mixed
use AI-generated questions instead of AP Statistics questionsAI-generated exams · item discriminationmean discrimination alpha: 1.2 -> 1.3No clear effect
use AI-generated exams instead of AP Statistics examsAI-generated exams · test informationmaximum test information: 2.61 -> 3.85Improved
use AI-generated exams instead of AP Statistics examsAI-generated exams · test reliabilityreliability at peak: 0.72 -> 0.79Improved
use AI-generated exams instead of AP Statistics examsAI-generated exams · test information at theta=0test information: 2.5 -> 3.36Improved
use AI-generated questions instead of AP Statistics questionsAI-generated exams · share of highly or very highly discriminating itemsshare of items (%): 21 -> 36Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy