AIGENIE: free R package writes psychometric test items and prunes weak ones with AI
GolinoHudson · x · 2026-10-30
Sergio Escorial (UCM) walks through the paper and open-source tool AIGENIE (free on CRAN for non-commercial use) by Russell-Lasalandra, Golino, Garrido and Christensen, targeting the classic pain of scale development: experts drafting items, running pilots, and iterating for months before validating the structure.
AIGENIE belongs to the emerging field of Generative Psychometrics, premised on the idea that item text already contains much of the information psychometricians need, evaluable algorithmically. It delivers three steps: writing items with AI, turning them into numbers, and pruning weak ones via network psychometrics before a single response is collected. Supporting prior work: Fyffe et al. (2024) showed transformers identify an item's target construct more accurately than human raters; Hernandez & Nie (2023) predicted item-item correlations from text alone.
For researchers, months-long scale development can now be massively compressed, with a full tutorial in the paper.
Related event: AIGENIE: Open-Source R Package Generates Psychometric Scale Items with LLMs(3 posts)→
More from Research
- Physicist calls OpenAI's Navier-Stokes solution physically meaningless despite loophole win — GaryMarcus · 2026-10-30
- ELLIS x UniReps talk: why distinct learning processes yield similar representations — ClementineDomi6 · 2026-10-30
- Anthropic paper: 0.1% pretraining poison plants RCE backdoor in 4B CLI agent — omarsar0 · 2026-10-30
- CopeNLU presents 7 papers at EMNLP 2026 on bias, alignment, explainability — IAugenstein · 2026-10-30
- Two-stage 3D ResNet pipeline detects neonatal brain pathologies from MRI with 0.919 AUC — Dr_Alex_Crimi · 2026-10-30
- 40 years of putting new neurons into the CNS: why so slow, and can AI accelerate it? — patrickmineault · 2026-10-30