{"id":"W4405023785","doi":"10.1109/cvpr52734.2025.01822","title":"All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages","year":2025,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Benchmark (surveying); Computer science; Resource (disambiguation); Artificial intelligence; Data science; Natural language processing; Geography","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002259962,0.0001331229,0.0001140626,0.0001067785,0.0001456006,0.0001701343,0.0008246913,0.00004464907,0.0002970384],"category_scores_gemma":[0.00009842736,0.0001033677,0.00005403201,0.0002794676,0.00002225358,0.0001517576,0.0003273371,0.000180007,0.001511754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000452554,"about_ca_system_score_gemma":0.00002664893,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001488274,"about_ca_topic_score_gemma":0.00003767823,"domain_scores_codex":[0.998931,0.00009073329,0.000154147,0.0003852016,0.0002258689,0.0002130732],"domain_scores_gemma":[0.999044,0.0001833204,0.00005771537,0.0006081515,0.00005711572,0.0000496767],"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":[0.00002040596,0.0003822123,0.06549941,0.00009894813,0.0001818474,0.00003301172,0.006038045,0.007720529,0.02760783,0.40981,0.07573645,0.4068713],"study_design_scores_gemma":[0.001348968,0.0001783422,0.7105346,0.0001547792,0.00005318938,0.00001283146,0.001671235,0.2619153,0.006182518,0.002299559,0.01485008,0.0007986035],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4819218,0.0001297773,0.09037516,0.03415687,0.0002114884,0.000567986,0.000006096519,0.001313802,0.391317],"genre_scores_gemma":[0.9151319,0.000002596426,0.06569078,0.006526785,0.00004190255,0.00004182721,0.00001037553,0.000006864273,0.01254699],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6450351,"threshold_uncertainty_score":0.9992657,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02232824207649547,"score_gpt":0.3794272945488076,"score_spread":0.3570990524723121,"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."}}