Research

Paper

AI LLM March 13, 2026

Developing the PsyCogMetrics AI Lab to Evaluate Large Language Models and Advance Cognitive Science -- A Three-Cycle Action Design Science Study

Authors

Zhiye Jin, Yibai Li, K. D. Joshi, Xuefei, Deng, Xiaobing, Li

Abstract

This study presents the development of the PsyCogMetrics AI Lab (psycogmetrics.ai), an integrated, cloud-based platform that operationalizes psychometric and cognitive-science methodologies for Large Language Model (LLM) evaluation. Framed as a three-cycle Action Design Science study, the Relevance Cycle identifies key limitations in current evaluation methods and unfulfilled stakeholder needs. The Rigor Cycle draws on kernel theories such as Popperian falsifiability, Classical Test Theory, and Cognitive Load Theory to derive deductive design objectives. The Design Cycle operationalizes these objectives through nested Build-Intervene-Evaluate loops. The study contributes a novel IT artifact, a validated design for LLM evaluation, benefiting research at the intersection of AI, psychology, cognitive science, and the social and behavioral sciences.

Metadata

arXiv ID: 2603.13126
Provider: ARXIV
Primary Category: q-bio.NC
Published: 2026-03-13
Fetched: 2026-03-16 06:01

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.13126v1</id>\n    <title>Developing the PsyCogMetrics AI Lab to Evaluate Large Language Models and Advance Cognitive Science -- A Three-Cycle Action Design Science Study</title>\n    <updated>2026-03-13T16:17:45Z</updated>\n    <link href='https://arxiv.org/abs/2603.13126v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.13126v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>This study presents the development of the PsyCogMetrics AI Lab (psycogmetrics.ai), an integrated, cloud-based platform that operationalizes psychometric and cognitive-science methodologies for Large Language Model (LLM) evaluation. Framed as a three-cycle Action Design Science study, the Relevance Cycle identifies key limitations in current evaluation methods and unfulfilled stakeholder needs. The Rigor Cycle draws on kernel theories such as Popperian falsifiability, Classical Test Theory, and Cognitive Load Theory to derive deductive design objectives. The Design Cycle operationalizes these objectives through nested Build-Intervene-Evaluate loops. The study contributes a novel IT artifact, a validated design for LLM evaluation, benefiting research at the intersection of AI, psychology, cognitive science, and the social and behavioral sciences.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='q-bio.NC'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-13T16:17:45Z</published>\n    <arxiv:comment>10 pages. Prepared: April 2025; submitted: June 15, 2025; accepted: August 2025. In: Proceedings of the 59th Hawaii International Conference on System Sciences (HICSS 2026), January 2026</arxiv:comment>\n    <arxiv:primary_category term='q-bio.NC'/>\n    <arxiv:journal_ref>Proceedings of the 59th Hawaii International Conference on System Sciences (HICSS), January 2026, pp. 6952-6961</arxiv:journal_ref>\n    <author>\n      <name>Zhiye Jin</name>\n      <arxiv:affiliation>Nancy</arxiv:affiliation>\n    </author>\n    <author>\n      <name>Yibai Li</name>\n      <arxiv:affiliation>Nancy</arxiv:affiliation>\n    </author>\n    <author>\n      <name>K. D. Joshi</name>\n      <arxiv:affiliation>Nancy</arxiv:affiliation>\n    </author>\n    <author>\n      <name> Xuefei</name>\n      <arxiv:affiliation>Nancy</arxiv:affiliation>\n    </author>\n    <author>\n      <name> Deng</name>\n      <arxiv:affiliation>Emily</arxiv:affiliation>\n    </author>\n    <author>\n      <name> Xiaobing</name>\n      <arxiv:affiliation>Emily</arxiv:affiliation>\n    </author>\n    <author>\n      <name> Li</name>\n    </author>\n  </entry>"
}