{"id":"W4399434480","doi":"10.1007/s10639-024-12771-3","title":"Exploring quality criteria and evaluation methods in automated question generation: A comprehensive survey","year":2024,"lang":"en","type":"article","venue":"Education and Information Technologies","topic":"Topic Modeling","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Quality (philosophy); Computer science; Educational technology; Evaluation methods; Management science; Data science; Mathematics education; Psychology; Engineering; Reliability engineering; Epistemology","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":[],"consensus_categories":[],"category_scores_codex":[0.001686134,0.0000811096,0.00009137023,0.0004432008,0.00007151075,0.0004536317,0.0001103665,0.00006820877,0.000002781993],"category_scores_gemma":[0.0004912755,0.00007807647,0.000008491214,0.0004669889,0.00003059061,0.005561208,0.00009062535,0.00009932216,0.000004938458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008182548,"about_ca_system_score_gemma":0.0001329517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001490756,"about_ca_topic_score_gemma":0.00001470085,"domain_scores_codex":[0.9990248,0.0002482317,0.000341022,0.0001650223,0.000135494,0.00008541262],"domain_scores_gemma":[0.999393,0.000111949,0.00006621264,0.0001991087,0.0002138819,0.00001588483],"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":[8.255882e-7,0.00000751298,0.0003386331,0.00005631847,0.000002796413,3.479686e-8,0.002358506,0.0001012535,0.0004609788,0.05237167,0.0002171869,0.9440843],"study_design_scores_gemma":[0.00008255814,0.00001372204,0.07296114,0.00005346548,0.000002064438,0.000006114776,0.001647946,0.918637,0.001439467,0.002812071,0.00224009,0.0001043545],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5402408,0.001711444,0.4517506,0.002735147,0.001131778,0.0003148408,0.000002117258,0.001890062,0.0002232216],"genre_scores_gemma":[0.8680109,0.0004862983,0.131182,0.00009359547,0.0000165193,0.0001612006,0.00004224055,0.000002115812,0.000005114493],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9439799,"threshold_uncertainty_score":0.437438,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3294129269693888,"score_gpt":0.4810801104680509,"score_spread":0.1516671834986622,"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."}}