{"id":"W4307651087","doi":"","title":"Unsupervised multiple-choice question generation for out-of-domain Q&A fine-tuning","year":2022,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Expert finding and Q&A systems","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal; Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Domain (mathematical analysis); Artificial intelligence; Mathematics","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":[0.005045122,0.001090912,0.001721148,0.00136051,0.0008034566,0.001587152,0.003683839,0.002813291,0.01274742],"category_scores_gemma":[0.01815858,0.0007756707,0.001321811,0.0009310103,0.001128276,0.003048854,0.004163614,0.003115306,0.004887096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00115359,"about_ca_system_score_gemma":0.001758159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003726944,"about_ca_topic_score_gemma":0.006502264,"domain_scores_codex":[0.9950624,0.002717002,0.0002687314,0.001129859,0.0004840931,0.0003379724],"domain_scores_gemma":[0.9822984,0.01380696,0.0003369286,0.001678033,0.001381844,0.0004978287],"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":[0.00206964,0.001153301,0.003595347,0.0005547356,0.0002016181,0.0002765502,0.0007640982,0.05602021,0.02633831,0.01046535,0.02004264,0.8785183],"study_design_scores_gemma":[0.0001197173,0.00009934181,0.0005253343,0.00002132494,0.00003264752,0.00009362707,0.000114654,0.9770976,0.008130215,0.01119826,0.00254535,0.00002186642],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03974292,0.0005697635,0.9446625,0.0004920317,0.0001477503,0.0004009777,0.0006147284,0.01085922,0.002510058],"genre_scores_gemma":[0.4684546,0.0001206901,0.5232927,0.0003906496,0.0001208638,0.0004691438,0.002147833,0.0007105498,0.004293003],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01274742,"threshold_uncertainty_score":0.04264432,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05186674480851388,"score_gpt":0.2825924515621544,"score_spread":0.2307257067536405,"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."}}