From Prompt to Scale? Examining the Effects of Prompt Instructions on LLM-Generated Scales
Open accessAbstract
Abstract: Large language models (LLMs) have gained increased attention as tools for automatic item and scale generation in psychological assessment. Yet, it is not known how prompt instructions can affect the psychometric quality of LLM-generated items and scales. To test whether different prompt instructions influence the quality of generated items and scales, a general-purpose LLM (GPT4o) was prompted with seven different prompt instructions (one adhering to prompt engineering principles solely and six combining these principles with five different psychometric characteristics). Items were generated for two constructs, one established (emotional stability) and one rather novel (climate change anxiety). The LLM-generated items and scales were evaluated in terms of content validity, item difficulty, model fit, factor structure, reliability, and validity. Overall, there were no systematic differences regarding content validity, item difficulty, model fit, reliability and convergent validity, but unsystematic differences in terms of validity.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Development and validation of a measure of climate change anxiety
Clayton, S., & Karazsia, B. T. (2020) · Journal of Environmental Psychology · doi:10.1016/j.jenvp.2020.101434 · Cited by 1,196 · see citing works
Wullenkord, M. C., Tröger, J., Hamann, K. R. S., Loy, L. S., & Reese, G. (2021) · Climatic Change · doi:10.1007/s10584-021-03234-6 · Cited by 344 · see citing works
Flagged first, then by citations
- Authors
- Oeljeklaus, L., Höft, S., & Danner, D.
- Affiliations
- Heidelberg University (DE)
- Department of Psychology, University of Applied Labour Studies, Mannheim, Germany
- Venue
- Psychological Test Adaptation and Development
- Publisher
- Hogrefe Publishing Group
- Published
- 2026-07-01
- Volume
- 7
- Pages
- 279-288
- ISSN
- 2698-1866 (ISSN-L)
- OpenAlex
- W7168615648
- Cited by
- 1
- References
- 2
- Citations by year
- 2026: 1
- FWCI
- 3.85
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- Locations
- Psychological Test Adaptation and Development (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- OSF Preprints (OSF Preprints) (submittedVersion)
- Open Science Framework
- Topics
- Social Sciences › Decision Sciences › Management Science and Operations Research › Psychometric Methodologies and Testing
- Social Sciences › Psychology › Applied Psychology › Psychological Testing and Assessment
- Social Sciences › Education › Health Education and Validation
- Keywords
- large language models, prompt engineering, automatic item generation, psychometric properties, GPT-4o, emotional stability, climate anxiety, content validity, factor structure, reliability statistics, convergent validity, item difficulty
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
