Using Artificial Intelligence in Test Construction: A Practical Guide

Key Points

Validity, reliability, and fairness are critical for effective test development using artificial intelligence.
Specific guidelines link each challenge to practices that promote responsible implementation of AI in tests.
The approach emphasizes the importance of calibration to maintain quality in AI-generated tests.
Implementing these practical guidelines can improve overall test integrity and stakeholder confidence.

Abstract

We propose a practical guide for using generative AI in test development and calibration, targeting challenges related to validity, reliability, and fairness by linking each issue to specific guidelines that promote responsible, effective implementation.

Read Full Paperexternally

Connected Papers

Building similarity graph...

Analyzing shared references across papers

Discussion

Journals

Psicothema

Institutions

University of Massachusetts Amherst

Georgetown University

Universidad de Londres

References and Citations

Add This Paper to Your Research Feed

Any time a new paper drops it will be there.