Get Started
Research questionHow can valid personality situational judgment tests be developed without heavy subject-matter-expert labor?Creating personality situational judgment tests requires substantial expert effort and time, while their items must still represent the intended traits and support reliable measurement.
AI
Evaluation & Benchmarks
Natural Language Processing
Latest papersRecent research connected to this question, newest first.Automatic Item Generation for Personality Situational Judgment Tests with Large Language ModelsThe evidence concerns automated generation of personality SJTs with large language models, including GPT-4 and ChatGPT-5, across five Big Five facets. It includes prompt and temperature comparisons, repeated cross-model generation, and psychometric evaluation; most facets showed satisfactory reliability and validity, but compliance convergent validity and some criterion-related validity remained limited.research paper · Sep 1, 2026
Related questions
How reliably do human psychometric questionnaires predict LLM behavior in realistic user interactions?When does persona prompting improve LLM survey-response prediction, and how should attributes be selected?How can LLM judges produce reliable, unbiased scores for subjective, interdependent multi-step creativity tasks?How can we assess whether LLM-generated personas reproduce culturally conditioned worldviews and moral values?
Home
Topics
Search
Library