{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.007800262,0.00036967,0.0004895942,0.0003194895,0.0006554791,0.000468754,0.002360849,0.0002773409,0.00003823838],"category_scores_gemma":[0.003600223,0.0004172508,0.0003067559,0.0003995075,0.00009531304,0.0002575718,0.00178481,0.0005512163,0.00001097029],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002322519,"about_ca_system_score_gemma":0.0003365655,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001424854,"about_ca_topic_score_gemma":0.003113586,"domain_scores_codex":[0.9915916,0.005494526,0.0008322718,0.00108504,0.0006046231,0.0003919061],"domain_scores_gemma":[0.9911262,0.003352559,0.0008450466,0.002879682,0.001643913,0.000152632],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004778546,0.001892442,0.01639452,0.00145524,0.0003993489,0.000007260765,0.1246447,0.006079407,0.2469161,0.504047,0.01250546,0.08561069],"study_design_scores_gemma":[0.001959892,0.000003447324,0.001515204,0.002226643,0.0000552591,0.000009426672,0.0002355635,0.8001831,0.04297545,0.005339052,0.1441853,0.0013117],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07221322,0.0007757888,0.9166464,0.004356376,0.001568837,0.0008755774,0.00008365657,0.0003530908,0.003127109],"genre_scores_gemma":[0.5860944,0.00009373487,0.4056593,0.00008005959,0.0001408903,0.0005379517,0.001463903,0.00006148437,0.005868286],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7941036,"threshold_uncertainty_score":0.9998279,"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."}}