AI-GENIE uses LLMs to auto-generate validated psychometric scales, tested on N=4,964 samples
GolinoHudson · x · 2026-11-05
A University of Virginia team (Hudson Golino et al.) published the open-access AI-GENIE methodology in Behavior Research Methods: using LLMs to automatically generate psychometric scale items and validate them with network psychometrics, sharply reducing expert workload.
- Method: Mixtral, Gemma 2, Llama 3, GPT-3.5 and GPT-4o generated item pools mimicking Big Five personality scales, with network-psychometric metrics automatically screening quality and redundancy.
- Validation: Items were empirically tested on five nationally representative US samples (N=4,964 total), showing AI-GENIE scales achieve structural validity.
- Positioning: a rebuttal to "don't use AI to build assessments" — with the right tools, you can.
More from Research
- New Book on Generative AI and Stochastic Thermodynamics by Welling Team Out This Month — mjdramstead · 2026-11-05
- New paper uses 288M job postings to measure where AI raises the value of work it can't do — robseamans · 2026-11-05
- Matthew Honnibal: LLMs can 'see' weight matrices — but only one layer at a time — honnibal · 2026-11-05
- RicursiveAI claims 16x compute efficiency gain on code pretraining vs Olmo 3 baseline — samiramanabi · 2026-11-05
- Claude drifts from 🌀 to 💖: refined AI symbols become less legible to humans (67%→44%) — mimi10v3 · 2026-11-05
- Engram: brief training fixes long-run models' increasingly inscrutable notes — scott_linderman · 2026-11-05