{"id":"W7106810170","doi":"10.48448/ax2x-gs31","title":"FilBench: Can LLMs Understand and Generate Filipino?","year":2025,"lang":"","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Set (abstract data type); Comprehension; Reading (process); Value (mathematics); Work (physics); Benchmark (surveying)","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":[0.002208113,0.002276289,0.0006034634,0.002290623,0.001169491,0.002838807,0.002226678,0.002041996,0.01627506],"category_scores_gemma":[0.01382948,0.0003411561,0.000681026,0.00129977,0.0007690518,0.004769171,0.003024423,0.001845271,0.01083402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001798477,"about_ca_system_score_gemma":0.002260114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01996302,"about_ca_topic_score_gemma":0.02922329,"domain_scores_codex":[0.9986547,0.000468825,0.000108806,0.0003946361,0.000221353,0.0001516127],"domain_scores_gemma":[0.9953126,0.002336556,0.0001872784,0.000914241,0.0009561101,0.0002932469],"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":[0.001490784,0.0007845007,0.03588934,0.00302956,0.0003268117,0.001376439,0.002643039,0.06693336,0.01222085,0.006506934,0.2739711,0.5948274],"study_design_scores_gemma":[0.0004457969,0.001080494,0.03575801,0.0008761113,0.000223711,0.001031828,0.007345502,0.6277258,0.06289204,0.0204898,0.2418301,0.0003008553],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5460221,0.005083947,0.09331243,0.00649034,0.001603931,0.001068274,0.07816423,0.1729993,0.09525543],"genre_scores_gemma":[0.7344614,0.0009485275,0.08713401,0.001278065,0.0001498832,0.0006359916,0.1532941,0.00487884,0.01721931],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01996302,"threshold_uncertainty_score":0.05444545,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07341646600549298,"score_gpt":0.318754006496707,"score_spread":0.245337540491214,"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."}}