Article

Estimating Dimensional Structure in Generative Psychometrics: Comparing PCA and Network Methods Using Large Language Model Item Embeddings

2025-12-30

Abstract excerpt

<p>As large language models (LLMs) increasingly inform psychometric practice through item generation and semantic analysis, embedding-based approaches offer a pre-empirical pathway for assessing dimensional structure before human response data become available. However, the methodological choices used to recover dimensions from embedding spaces remain underexamined. The present study compared the performance of pr...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: f6f01833-b510-519c-a2f2-eed387fc1328
DOI: 10.31234/osf.io/2s7pw_v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Estimating Dimensional Structure in Generative Psychometrics: Comparing PCA and Network Methods Using Large Language Model Item EmbeddingsDOI 10.31234/osf.io/2s7pw_v1Read

Let the Algorithm Speak: How to Use Neural Networks for Automatic Item Generation in Psychological Scale DevelopmentSemantic proximity Read

Enhancing Scale Development: Pseudo Factor Analysis of Language Embedding Similarity MatricesSemantic proximity Read

Leveraging AI for Automatic Item Generation for Psychological ScalesSemantic proximity Read

How to automatically document data with the codebook package to facilitate data re-useSemantic proximity Read

Transformer-Based Deep Neural Language Modeling for Construct-Specific Automatic Item GenerationSemantic proximity Read

Evaluating Large Language Models for Feature Extraction from Verbal Stimuli: A Simulation-Based WorkflowSemantic proximity Read

Sample Size Planning in Item Response Theory: A TutorialSemantic proximity Read

A High-Dimensional Data-Driven Modularity Analysis Reveals Five Distinct Personality Clusters with Different Psychological ProfilesSemantic proximity Read

Cognitive arbitration between candidate dimensions of psychopathologySemantic proximity Read