AI-GENIE: LLMs auto-generate validated psychological scales, now with 4k+ downloads
GolinoHudson · x · 2026-10-29
AI-GENIE (Automatic Item Generation and Validation via Network-Integrated Evaluation) uses LLMs plus network psychometrics to auto-generate and select high-quality, non-redundant psychological assessment items, cutting reliance on expert intervention.
The team validated it with Monte Carlo simulations using Mixtral, Gemma 2, Llama 3, GPT-3.5 and GPT-4o to generate Big Five-style item pools, then tested the scales on five nationally representative US samples (N=4,964 total), showing structural validity. Published open-access in Behavior Research Methods, it now has 4k+ downloads and 50+ citations.
More from Research
- New paper challenges JEPA feature-selection theory: unpredictable features can be kept — andreea7b · 2026-10-29
- SREGym to debut at Bench Summit, targeting AI SRE evaluation frontier — tianyin_xu · 2026-10-29
- AA-Robotics benchmark: GPT-6 Astra tops robot-arm control, still ~100x slower than humans — ArtificialAnlys · 2026-10-29
- Delta-Matching closes the FP8 attention gap: all 7 core matmuls in FP8, loss matches BF16 — songhan_mit · 2026-10-29
- RFD4-Proteina lands on Hugging Face as HF publishes its October AI for Science roundup — AllThingsApx · 2026-10-29
- Google's PLE: 85 real engineering tasks, best agent config scores only 50.6% — rohanpaul_ai · 2026-10-29