AIED
Measuring What Matters---or What’s Convenient?: Robustness of LLM-Based Scoring Systems to Construct-Irrelevant Factors
Mon Jun 29, 9:00 AM–9:15 AM · Room 101
Automated Assessment & Scoring Psychometrics & Educational Measurement Generative AI & Large Language Models Explainable & Trustworthy AI
Probes whether LLM-based scoring systems are sensitive to construct-irrelevant factors, raising questions about what these systems actually measure.