{"id":"W7148294870","doi":"10.1109/asru65441.2025.11434707","title":"mSTEB: Massively Multilingual Evaluation of LLMs on Speech and Text Tasks","year":2025,"lang":"","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"Google","keywords":"Benchmark (surveying); Spoken language; Range (aeronautics); Task (project management); Government (linguistics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008874688,0.00354833,0.001609111,0.002571805,0.001339539,0.002565583,0.002737991,0.002283023,0.007908073],"category_scores_gemma":[0.02436817,0.0006873187,0.001679066,0.001857263,0.0009378439,0.005403996,0.005282431,0.003063309,0.006026426],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001410508,"about_ca_system_score_gemma":0.002604631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01895973,"about_ca_topic_score_gemma":0.02269046,"domain_scores_codex":[0.9921347,0.003879303,0.0006987255,0.001637972,0.001205276,0.0004439235],"domain_scores_gemma":[0.9899397,0.005625255,0.0002671033,0.001624638,0.00181666,0.0007266376],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.005851539,0.002888595,0.01660567,0.003761041,0.002854593,0.0008149598,0.001324018,0.113988,0.02372202,0.003432101,0.2284928,0.5962645],"study_design_scores_gemma":[0.001468571,0.002908585,0.01768817,0.0003162726,0.0007985716,0.0008699282,0.001876666,0.8553721,0.04547599,0.01108472,0.06177267,0.0003678823],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5177861,0.0133502,0.1951368,0.002855405,0.00379069,0.001855071,0.05109238,0.17781,0.03632332],"genre_scores_gemma":[0.6744504,0.001454923,0.1339989,0.001213541,0.0005421653,0.001344622,0.1696923,0.006373028,0.01093023],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01895973,"threshold_uncertainty_score":0.04693437,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05745102832357502,"score_gpt":0.3425811171436254,"score_spread":0.2851300888200504,"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."}}