Saved in:
Bibliographic Details
Main Authors: Lee, Grandee, Wang, Yue, Lye, Che Yee, Peh, Luke
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.19529
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913146110738432
author Lee, Grandee
Wang, Yue
Lye, Che Yee
Peh, Luke
author_facet Lee, Grandee
Wang, Yue
Lye, Che Yee
Peh, Luke
contents When the same LLM generates assessment items, simulates student responses, and scores them, the validation loop is self-referential. We introduce Generative-Evaluative Agreement (GEA), a validity criterion measuring whether an LLM's scoring function recovers the skill levels its generative function was instructed to produce. In the first direct measurement of GEA on a two-stage adaptive assessment, the model recovers roughly half the intended variance r = 0.698 with systematic positive bias. GEA is strong r > 0.7 for syntactically verifiable skills but near zero for design-level skills, and low-skill overestimation inflates scores near the routing threshold. We argue that granular, skill-decomposed rubrics are the principal proposed mechanism for strengthening GEA and outline complementary mitigations.
format Preprint
id arxiv_https___arxiv_org_abs_2605_19529
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Generative-Evaluative Agreement: A Necessary Validity Criterion for LLM-Enabled Adaptive Assessment
Lee, Grandee
Wang, Yue
Lye, Che Yee
Peh, Luke
Artificial Intelligence
When the same LLM generates assessment items, simulates student responses, and scores them, the validation loop is self-referential. We introduce Generative-Evaluative Agreement (GEA), a validity criterion measuring whether an LLM's scoring function recovers the skill levels its generative function was instructed to produce. In the first direct measurement of GEA on a two-stage adaptive assessment, the model recovers roughly half the intended variance r = 0.698 with systematic positive bias. GEA is strong r > 0.7 for syntactically verifiable skills but near zero for design-level skills, and low-skill overestimation inflates scores near the routing threshold. We argue that granular, skill-decomposed rubrics are the principal proposed mechanism for strengthening GEA and outline complementary mitigations.
title Generative-Evaluative Agreement: A Necessary Validity Criterion for LLM-Enabled Adaptive Assessment
topic Artificial Intelligence
url https://arxiv.org/abs/2605.19529