{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005157304,0.00006613735,0.00009774009,0.00003229005,0.0002621189,0.000135157,0.000200866,0.00004928316,0.0001710301],"category_scores_gemma":[0.00006751106,0.00003801031,0.00005693155,0.000239158,0.0002370885,0.0001992842,0.00004969241,0.00007221065,0.00002857498],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001393951,"about_ca_system_score_gemma":0.00009270526,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03081872,"about_ca_topic_score_gemma":0.003273778,"domain_scores_codex":[0.9989907,0.0001523135,0.0001201512,0.0001637761,0.0004058517,0.0001671883],"domain_scores_gemma":[0.9992115,0.0005593624,0.00002348311,0.00009878188,0.00003723904,0.00006961331],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00002049609,0.00001243401,0.00001020646,0.000009652429,0.0000553203,0.00001617836,0.8384107,0.01092944,0.002994553,0.09829018,0.03971032,0.009540563],"study_design_scores_gemma":[0.0001077682,0.00006320878,0.000007008177,0.0001077438,0.0000270592,1.90205e-7,0.7978875,0.1840781,0.0002540472,0.01608935,0.001276319,0.0001016325],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8106369,0.002538725,0.07584558,0.005463299,0.0006053562,0.0004205795,0.00001899769,0.0001863342,0.1042842],"genre_scores_gemma":[0.9961825,0.00008573302,0.0008095418,0.00009289326,0.0001675171,0.000001860636,0.00000179263,0.000005234247,0.002652933],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1855455,"threshold_uncertainty_score":0.9756351,"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."}}