The Ultimate Tutorial for AI-driven Scale Development in Generative Psychometrics: Releasing AIGENIE from its Bottle

arXiv cs.AI / 3/31/2026

💬 OpinionSignals & Early TrendsTools & Practical UsageModels & Research

共有:

Key Points

The article presents a tutorial for the AIGENIE R package, which implements the AI-GENIE framework to automate early psychometric scale-development workflows using LLM-generated items plus network-based evaluation methods.
AIGENIE generates candidate item pools with large language models, converts item text into high-dimensional embeddings, and then applies a reduction pipeline using Exploratory Graph Analysis (EGA), Unique Variable Analysis (UVA), and bootstrap EGA to validate item structure entirely in silico.
The tutorial walks through installation/setup, API usage, LLM text generation, item generation, and the specific AIGENIE() and GENIE() functions, including six structured parts and two running examples (Big Five and AI Anxiety).
The package is designed to be flexible about model sourcing, supporting multiple LLM providers (OpenAI, Anthropic, Groq, HuggingFace, and local models) and offering a fully offline mode with no external API calls.
GENIE() is provided for researchers to reuse the same network psychometric reduction pipeline on previously created item pools, broadening applicability beyond LLM-generated candidates.

Abstract

Psychological scale development has traditionally required extensive expert involvement, iterative revision, and large-scale pilot testing before psychometric evaluation can begin. The `AIGENIE` R package implements the AI-GENIE framework (Automatic Item Generation with Network-Integrated Evaluation), which integrates large language model (LLM) text generation with network psychometric methods to automate the early stages of this process. The package generates candidate item pools using LLMs, transforms them into high-dimensional embeddings, and applies a multi-step reduction pipeline -- Exploratory Graph Analysis (EGA), Unique Variable Analysis (UVA), and bootstrap EGA -- to produce structurally validated item pools entirely *in silico*. This tutorial introduces the package across six parts: installation and setup, understanding Application Programming Interfaces (APIs), text generation, item generation, the `AIGENIE` function, and the `GENIE` function. Two running examples illustrate the package's use: the Big Five personality model (a well-established construct) and AI Anxiety (an emerging construct). The package supports multiple LLM providers (OpenAI, Anthropic, Groq, HuggingFace, and local models), offers a fully offline mode with no external API calls, and provides the `GENIE()` function for researchers who wish to apply the psychometric reduction pipeline to existing item pools regardless of their origin. The `AIGENIE` package is freely available on R-universe at https://laralee.r-universe.dev/AIGENIE.