The Unsampled Truth: Psychometrics in SLMs Measure Prompt Artifacts, Not Psychological Constructs
For researchers using SLMs in psychometrics, this work reveals that current models fail to simulate psychological traits, but provides a diagnostic framework to identify artifacts.
The paper shows that psychometric assessments from small language models (0.6B-14B) are dominated by prompt artifacts rather than semantic reasoning, limiting their utility for measuring psychological constructs.
When prompting SLMs for psychometric assessments, researchers assume the outputs reflect semantic reasoning. We evaluate this premise across 13 open-weights models (0.6B to 14B parameters) using a prompt variation framework that separates semantic signals from prompt artifacts. By systematically varying personas, instructions, items, and option symbols, we find that artifactual variance frequently overpowers the semantic signal. In these cases, models predominantly reflect prompt compliance rather than simulated psychological traits. While these findings limit SLM utility in psychometrics, our framework provides a diagnostic tool to identify destructive artifacts and isolate semantic understanding for future frontier-model research.