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

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.

Figures (8)

• Figure 1: The six steps of the AIGENIE item pool reduction pipeline. Step 0 (which occurs before item reduction) is obtain the initial item pool (either by generating items using an LLM or manually writing them). Step 1 is generate the item embeddings using an LLM. Steps 2--6 involve using network psychometric techniques to whittle down the item pool algorithmically.
• Figure 2: When using AIGENIE in the in-built prompt mode, the function takes the user-specified components (e.g., domain, prompt.notes, item.type.definitions, or scale.title) and uses them to build a strong prompt automatically.
• Figure 3: A plot showing the EGA network before item reduction (on the left) compared to the network after item reduction (on the right) for Agreeableness items.
• Figure 4: The stability of the EGA network before reduction (left) versus after (right) reduction. The stability plot shows a massive improvement in stability post-reduction. Additionally, the NMI has increased by about 4%
• Figure 5: The EGA network before (left) vs after (right) reduction for AI Learning anxiety items. The NMI improved by 9.48%. The final NMI is 86.91%