Targeting zero false negatives and 98% accuracy leaves about a 10% teacher workload reduction with accuracy slightly above 98%¶
Claim · All claims
Evidence · 1 study · designr2·q2
Currency · newest study 2023 · 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? Setting a maximum false-negative rate of 0% and minimum accuracy of 98% still allows the autograder to grade slightly above 10% of answers at accuracy slightly above 98%. → Johannes Schneider 2023
Evidence¶
Johannes Schneider 2023¶
Johannes Schneider, Robin Richner, Micha Riser. (2023). Towards Trustworthy AutoGrading of Short, Multi-lingual, Multi-type Answers. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-022-00289-z
q2 · i? · design · r2
Numerical evaluation on test data simulating a teaching-assistant accuracy level, using thresholds derived from the accuracy constraint. The article reports "a possible workload reduction of slightly above 10% and overall accuracy of slightly above 98%" under these constraints.
"If we use C c min = 0.98 and we do not allow the autograder to fail any students, we get a possible workload reduction of slightly above 10% and overall accuracy of slightly above 98%."
Discussion¶
Related Claims¶
- Deferring difficult question-answer pairs to humans raises grading accuracy, with 62% of samples classified at 92% accuracy — related
- Autograding is most accurate for numeric answers, and error rates vary less than 8% across languages — related
- Two attempted workload-reduction refinements—stopword-based question demoting and supplementing training data with answers labeled incorrect from other questions—did not improve classification results overall — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
zero-false-negative-target-yields-10-percent-workload-reduction |
title |
Targeting zero false negatives and 98% accuracy leaves about a 10% teacher workload reduction with accuracy slightly above 98% |
description |
Targeting zero false negatives and 98% accuracy leaves about a 10% teacher workload reduction with accuracy slightly above 98% |
status |
review |
evidence_strength |
weak |
newest_evidence |
2023 |
generated |
by process:wiki-ingest on 2026-10-27 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — johannes-schneider-2023 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.