{"id":"W6966828973","doi":"10.48448/d8n2-0842","title":"Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Indonesian; Fluency; Quality (philosophy); Adaptation (eye); First language; Second language; Data quality; Cultural diversity","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003231202,0.0008521733,0.0008480524,0.00232199,0.0003277955,0.000993871,0.001885331,0.0002692048,0.0001454241],"category_scores_gemma":[0.0003124218,0.0006769061,0.00003767823,0.003419129,0.002327937,0.0004331201,0.002207998,0.001057307,0.0009261661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005145956,"about_ca_system_score_gemma":0.001364126,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.06441779,"about_ca_topic_score_gemma":0.6511676,"domain_scores_codex":[0.9937969,0.000381831,0.0007924873,0.002604453,0.001334949,0.001089423],"domain_scores_gemma":[0.9961566,0.00009765611,0.0003711765,0.002694358,0.0001566152,0.0005235391],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001774741,0.00371132,0.01514004,0.0006449554,0.0004392368,0.3077615,0.01867451,0.0001851082,0.005002778,0.0009159276,0.6383051,0.009041965],"study_design_scores_gemma":[0.01808462,0.004408391,0.003722137,0.005333965,0.002581366,0.1466707,0.1849753,0.1821749,0.0002643456,0.001950469,0.4335431,0.01629069],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9483733,0.003862046,0.00001533084,0.001700022,0.00195823,0.005136139,0.005053768,0.001521926,0.03237923],"genre_scores_gemma":[0.8966005,0.00009196092,0.002342575,0.0001774497,0.000445394,0.0000478592,0.0004079897,0.001231927,0.0986543],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5867498,"threshold_uncertainty_score":0.9998517,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06780032652354043,"score_gpt":0.3561537827351988,"score_spread":0.2883534562116583,"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."}}