{"id":"W4389519614","doi":"10.18653/v1/2023.emnlp-main.1040","title":"JASMINE: Arabic GPT Models for Few-Shot Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Alliance de recherche numérique du Canada; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Arabic; Islam; Computer science; Natural language processing; Artificial intelligence; Linguistics; History; Philosophy; Archaeology","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0003124776,0.00008604074,0.0001047351,0.0000972251,0.0001206929,0.0001027471,0.0005221554,0.00004214756,0.0000148786],"category_scores_gemma":[0.00004973003,0.00007732806,0.00006056442,0.0003079222,0.000008367242,0.0003653977,0.000208562,0.00009197488,0.000141728],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001808237,"about_ca_system_score_gemma":0.00003365396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002117375,"about_ca_topic_score_gemma":0.000005142688,"domain_scores_codex":[0.9990172,0.00001801993,0.0001523899,0.0003408332,0.0001655923,0.0003059402],"domain_scores_gemma":[0.999394,0.0001223196,0.00002994918,0.0003423672,0.00005107133,0.00006027244],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002733858,0.00001294804,0.0001309578,0.00002702912,0.0000117229,0.000006080961,0.0009478718,0.5371144,0.0007796613,0.394022,0.004215518,0.06272905],"study_design_scores_gemma":[0.0001519528,0.00002434431,0.00004234974,0.000006141336,0.000001513096,0.000002162413,0.00003601932,0.9653478,0.0003735187,0.02997974,0.003929705,0.000104754],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01256597,0.00002091158,0.9736963,0.001451968,0.0002642482,0.000142188,3.229827e-7,0.0007641631,0.01109396],"genre_scores_gemma":[0.847999,0.000009360127,0.1307618,0.0003329186,0.0001134997,0.00005059653,0.000003406747,0.00001336015,0.02071606],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8429344,"threshold_uncertainty_score":0.3153347,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08778298209702809,"score_gpt":0.2933530634055287,"score_spread":0.2055700813085007,"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."}}