AI RESEARCH
Measuring What Matters -- or What's Convenient?: Robustness of LLM-Based Scoring Systems to Construct-Irrelevant Factors
arXiv CS.AI
•
ArXi:2603.25674v1 Announce Type: cross Automated systems have been widely adopted across the educational testing industry for open-response assessment and essay scoring. These systems commonly achieve performance levels comparable to or superior than trained human raters, but have frequently been nstrated to be vulnerable to the influence of construct-irrelevant factors (i.e., features of responses that are unrelated to the construct assessed) and adversarial conditions.