{"id":"W4404782787","doi":"10.18653/v1/2024.emnlp-main.385","title":"From Local Concepts to Universals: Evaluating the Multicultural Understanding of Vision-Language Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Religious Tourism and Spaces","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Problem of universals; Multiculturalism; Computer science; Natural language processing; Artificial intelligence; Linguistics; Cognitive science; Sociology; Psychology; Philosophy; Pedagogy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04783751,0.0009839274,0.0009782079,0.002610376,0.0026278,0.007843014,0.002234386,0.001957648,0.006818996],"category_scores_gemma":[0.1803924,0.0004857706,0.001663853,0.00153427,0.009416543,0.01614677,0.0104612,0.004060494,0.0004015111],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006506948,"about_ca_system_score_gemma":0.00355524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01260864,"about_ca_topic_score_gemma":0.01066511,"domain_scores_codex":[0.9689354,0.02352255,0.001149408,0.002238382,0.003359551,0.0007947053],"domain_scores_gemma":[0.7803115,0.1827365,0.01145012,0.01154742,0.0101429,0.003811599],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01599187,0.005485649,0.1972445,0.00378626,0.002567398,0.0006109251,0.3319233,0.03892558,0.004796068,0.1880912,0.003632583,0.2069447],"study_design_scores_gemma":[0.001796057,0.007588727,0.1284256,0.002641069,0.003598379,0.0006539587,0.3668548,0.1728481,0.008379665,0.2898871,0.01663667,0.0006898883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9454484,0.0005516073,0.01490821,0.001063901,0.00008133594,0.0003955918,0.0001397303,0.0000487806,0.03736233],"genre_scores_gemma":[0.9953306,0.0001117897,0.00374793,0.0001287848,0.00001331057,0.0001928827,0.0001269812,0.00002374196,0.0003239963],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04783751,"threshold_uncertainty_score":0.252992,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07245437785677805,"score_gpt":0.4178199730267422,"score_spread":0.3453655951699641,"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."}}