AIGENIE: Open-Source R Package Uses LLMs to Auto-Generate and Validate Psychometric Scales
GolinoHudson · x · 2026-10-31
Sergio Escorial walks through the paper "The Ultimate Tutorial for AI-driven Scale Development in Generative Psychometrics" (Russell-Lasalandra, Golino, Garrido, Christensen et al.) and its open-source companion AIGENIE.
- AIGENIE is a free-for-non-commercial R package on CRAN (Automatic Item Generation and Validation with Network-Integrated Evaluation) that drafts scale items, converts them to numbers, and prunes bad items via network analysis.
- The paper stakes out "generative psychometrics": item text already carries the information psychometricians need. Prior work (Fyffe et al. 2024) showed transformers identify an item's construct more accurately than human raters; Hernandez & Nie (2023) predicted item correlations from text.
- Traditional scale development takes months of expert drafting and piloting; AIGENIE aims to compress that with LLMs.
More from Research
- Image-Space Rule Discovery paper accepted to ACCV 2026, updated arXiv version released — HirokatuKataoka · 2026-10-31
- Measured: lossy engine flags drop a Q8_0 model to roughly Q2_0 quality — jesdga95 · 2026-10-31
- Paper with 25 coauthors argues a hardwired AI training pause is feasible via chip bans — birchlse · 2026-10-31
- 64 humans think aloud on ARC-AGI-3: dataset shows humans and LLMs learn worlds differently — xuanalogue · 2026-10-31
- Dana Moshkovitz presents proof of Unique Games Conjecture using alien error-correcting code — aran_nayebi · 2026-10-31
- MetaCircle Launches: Building AI That Discovers the Hidden Laws of AI Itself — ZimingLiu11 · 2026-10-31