The Unsampled Truth: Psychometrics in SLMs Measure Prompt Artifacts, Not Psychological Constructs
Mirrored from arXiv — NLP / Computation & Language for archival readability. Support the source by reading on the original site.
Computer Science > Computation and Language
Title:The Unsampled Truth: Psychometrics in SLMs Measure Prompt Artifacts, Not Psychological Constructs
Abstract: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.
| Comments: | 10 pages, 5 figures, 3 tables |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2606.03357 [cs.CL] |
| (or arXiv:2606.03357v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2606.03357
arXiv-issued DOI via DataCite (pending registration)
|
Access Paper:
- View PDF
- HTML (experimental)
- TeX Source
References & Citations
Bookmark
Bibliographic and Citation Tools
Code, Data and Media Associated with this Article
Demos
Recommenders and Search Tools
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
More from arXiv — NLP / Computation & Language
-
Hallucination Is Linearly Decodable from Mid-Layer Hidden States in Quantized LLMs
Jun 3
-
Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation
Jun 3
-
IdiomX A Multilingual Benchmark for Idiom Understanding, Retrieval, and Interpretation
Jun 3
-
Greener Than Humans? Environmental Attitudes in Large Language Models
Jun 3
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.