{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001145946,0.001219803,0.00106331,0.001065491,0.0007141747,0.001937816,0.0033846,0.002073368,0.01721268],"category_scores_gemma":[0.005954348,0.0006352887,0.001399989,0.0008826291,0.0003511076,0.003113645,0.002056465,0.003002184,0.01009649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001036098,"about_ca_system_score_gemma":0.001083385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01098897,"about_ca_topic_score_gemma":0.01802793,"domain_scores_codex":[0.9996077,0.00009692087,0.00002870831,0.0001379007,0.00009331141,0.00003542306],"domain_scores_gemma":[0.9990133,0.0004723916,0.00003555541,0.0001909713,0.0002224106,0.00006520285],"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":[0.0008982438,0.0003315591,0.001618449,0.0003910749,0.0002994552,0.0003098343,0.0002370121,0.2557761,0.00525484,0.01909574,0.08142474,0.6343631],"study_design_scores_gemma":[0.00003646783,0.00002971667,0.0001185233,0.00001816251,0.00001910702,0.00004449113,0.00002289076,0.9777867,0.001614026,0.01327449,0.007020964,0.00001445355],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01177322,0.001190008,0.9288076,0.0005798824,0.0003309673,0.0001755928,0.004160766,0.04731236,0.005669635],"genre_scores_gemma":[0.2163517,0.0009542903,0.7363662,0.0007958929,0.0002070862,0.0007099117,0.02125284,0.004780479,0.01858165],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01721268,"threshold_uncertainty_score":0.0575822,"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."}}