{"id":"W4407193212","doi":"10.3390/ai6020029","title":"Priv-IQ: A Benchmark and Comparative Evaluation of Large Multimodal Models on Privacy Competencies","year":2025,"lang":"en","type":"article","venue":"AI","topic":"Technology Adoption and User Behaviour","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Benchmark (surveying); Computer science; Artificial intelligence; Geography; Cartography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001748225,0.00009417086,0.0002350621,0.0003140916,0.0001144916,0.00003708546,0.000322591,0.00009513081,0.0001488408],"category_scores_gemma":[0.0004325894,0.0000716486,0.00004537,0.0004385825,0.0001361631,0.0002067227,0.0001506431,0.0001458971,0.00002687162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002778703,"about_ca_system_score_gemma":0.0000936908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001375779,"about_ca_topic_score_gemma":0.00004674387,"domain_scores_codex":[0.9982675,0.0001975384,0.0003462872,0.0002949892,0.0007647483,0.0001289666],"domain_scores_gemma":[0.9985678,0.0003249733,0.0001300151,0.0004016462,0.0005458627,0.00002972539],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0001644034,0.0008659352,0.3007361,0.00001049056,0.0000743101,0.000002219468,0.007020432,0.00341666,0.002199972,0.6175417,0.01620848,0.05175937],"study_design_scores_gemma":[0.00159423,0.0001087491,0.6478201,0.00004206657,0.00004717927,0.000001225113,0.00166726,0.2355682,0.001835854,0.1077121,0.003481618,0.0001213957],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9893726,0.0001976672,0.00357208,0.001570366,0.0001275739,0.0002930698,0.00002133984,0.00003701137,0.004808302],"genre_scores_gemma":[0.997942,0.000006747713,0.001245138,0.0003932728,0.000004443811,0.00001863692,0.000004427073,0.000001808134,0.0003835417],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5098296,"threshold_uncertainty_score":0.2921745,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2389025128290721,"score_gpt":0.4638331165797938,"score_spread":0.2249306037507217,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}