AIGENIE R Package Tutorial: LLMs Generate and Validate Psychometric Scales In Silico
GolinoHudson · x · 2026-10-06
An updated preprint presents the full tutorial for the AIGENIE R package implementing the AI-GENIE framework (Automatic Item Generation and Validation with Network-Integrated Evaluation): LLMs generate candidate item pools, which are embedded in high dimensions and passed through a multi-step reduction pipeline (EGA, UVA, bootstrap EGA) to produce structurally validated item pools entirely in silico — replacing the expert-heavy, iterative early stages of scale development.
The tutorial covers eight parts: setup, text generation, embeddings, item generation, the full AI-GENIE pipeline, the GENIE pipeline for researcher-supplied items, advanced prompt engineering, and fully local operation. Two running examples: Big Five personality and AI Anxiety. It supports OpenAI, Anthropic, Groq, HuggingFace, and local models, offers a fully offline mode with no external API calls, and is freely available on CRAN.
Related event: AIGENIE R Package Tutorial: LLM-Generated Psychometric Scale Items(2 posts)→
More from Research
- AI for Math Fund adds $17.1M from XTX Markets, backing 22 projects across 30 organizations — AlexKontorovich · 2026-10-06
- 62-person blind test of 48 LLM jokes shows models are getting funnier, Astra tops with 50%+ laughs — paraschopra · 2026-10-06
- Bayesian teaching dramatically improves probabilistic reasoning in LLMs, Nature Comms paper finds — tallinzen · 2026-10-06
- LiFT loops a DiT at inference: beats DiT-XL/2 with 52% less inference compute — cgmsnoek · 2026-10-06
- Researcher laments how slow humans look as algorithm design breakthroughs pile up — michaelchchoi · 2026-10-06
- Meta paper: dual coding agents cross-review lift correct patches from 45.8% to 62.5% — rohanpaul_ai · 2026-10-06