{"id":"W6891511957","doi":"10.48448/qbjb-af66","title":"AfriInstruct: Instruction Tuning of African Languages for Diverse Tasks","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Task (project management); Baseline (sea); Languages of Africa; Language model; Stability (learning theory); Language acquisition","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":[0.001402476,0.002501273,0.0006502077,0.0007547649,0.0006892968,0.001419736,0.002051421,0.001305069,0.01657716],"category_scores_gemma":[0.005314771,0.0005341664,0.001074701,0.0006728035,0.0005310248,0.003241665,0.002500131,0.003204376,0.01019899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006531093,"about_ca_system_score_gemma":0.001999047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01046051,"about_ca_topic_score_gemma":0.0192841,"domain_scores_codex":[0.9992562,0.000246992,0.00004264732,0.0002634857,0.00008859345,0.0001019944],"domain_scores_gemma":[0.9989591,0.0003266,0.00005672474,0.0003246027,0.0002223549,0.0001107338],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001339012,0.0007685366,0.0104972,0.0006838665,0.0004242187,0.000447834,0.0006680876,0.06788677,0.03259813,0.005080461,0.1794998,0.7001061],"study_design_scores_gemma":[0.0005685789,0.0005985364,0.005023978,0.0002247052,0.000222557,0.0004175029,0.0004189554,0.8519381,0.0523381,0.01214707,0.07589301,0.0002089107],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.3751916,0.005970233,0.3320113,0.004738702,0.003955821,0.0006870543,0.01517697,0.1972615,0.06500686],"genre_scores_gemma":[0.727606,0.0008959137,0.2076807,0.001920649,0.0002932937,0.0006633857,0.02388829,0.009639047,0.02741273],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01657716,"threshold_uncertainty_score":0.0554561,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02813317264915929,"score_gpt":0.3187061539515721,"score_spread":0.2905729813024128,"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."}}