Showing 1 - 3 of 3 Research Library Publications

Examining ChatGPT Performance on USMLE Sample Items and Implications for Assessment

Posted: | Victoria Yaneva, Peter Baldwin, Daniel P. Jurich, Kimberly Swygert, Brian E. Clauser

Academic Medicine: Volume 99 - Issue 2 - p 192-197

 

This report investigates the potential of artificial intelligence (AI) agents, exemplified by ChatGPT, to perform on the United States Medical Licensing Examination (USMLE), following reports of its successful performance on sample items. 

Category:Product-Oriented Research, USMLE, Assessment-Oriented Research, Applications of Technology

Three Sources of Validation Evidence Needed to Evaluate the Quality of Generated Test Items for Medical Licensure

Posted: | Mark Gierl, Kimberly Swygert, Donna Matovinovic, Allison Kulesher, Hollis Lai

Teaching and Learning in Medicine: Volume 33 - Issue 4 - p 366-381

 

The purpose of this analysis is to describe these sources of evidence that can be used to evaluate the quality of generated items. The important role of medical expertise in the development and evaluation of the generated items is highlighted as a crucial requirement for producing validation evidence.

Category:Assessment-Oriented Research, Other

Automated Item Generation with Recurrent Neural Networks

Posted: | M. von Davier

Psychometrika 83, 847–857 (2018)

 

Utilizing algorithms to generate items in educational and psychological testing is an active area of research for obvious reasons: Test items are predominantly written by humans, in most cases by content experts who represent a limited and potentially costly resource. Using algorithms instead has the appeal to provide an unlimited resource for this crucial part of assessment development.

Category:Assessment-Oriented Research, Applications of Technology