{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005583316,0.0006474723,0.0004853702,0.0009322166,0.0009229625,0.0009061046,0.001374824,0.001102128,0.002717732],"category_scores_gemma":[0.01745534,0.0002251468,0.0007135702,0.0009934239,0.0009973842,0.001488523,0.001947032,0.001480823,0.001471435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00121217,"about_ca_system_score_gemma":0.0008973316,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009635473,"about_ca_topic_score_gemma":0.01495775,"domain_scores_codex":[0.9958425,0.003043496,0.0002186675,0.0004787064,0.0002923172,0.0001243152],"domain_scores_gemma":[0.9860007,0.009288723,0.0002955708,0.002611016,0.001396444,0.0004074701],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.003747028,0.004385125,0.1126048,0.005476594,0.0005144787,0.007988021,0.02092645,0.1637906,0.0400917,0.01460483,0.1259501,0.4999202],"study_design_scores_gemma":[0.001256572,0.001958056,0.09996744,0.0008122238,0.0002562207,0.005036769,0.01847203,0.5544295,0.09177637,0.02672944,0.1989649,0.000340533],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9315765,0.001084101,0.03291153,0.002560552,0.000214078,0.0007251966,0.01411047,0.004734466,0.01208307],"genre_scores_gemma":[0.9063134,0.0002419967,0.06143053,0.0007391185,0.00006082465,0.0005255576,0.0268611,0.0005152881,0.003312158],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009635473,"threshold_uncertainty_score":0.02952772,"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."}}