{"id":"W7130683390","doi":"10.1109/swc65939.2025.00073","title":"Can Question Validation Criteria Improve the Quality of LLM-Generated Multiple-Choice Questions?","year":2025,"lang":"","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; Athabasca University","funders":"Alberta Innovates; Natural Sciences and Engineering Research Council of Canada; Athabasca University","keywords":"Formative assessment; Quality (philosophy); Set (abstract data type); Subject-matter expert; Quality assurance; Key (lock); Subject (documents)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003822915,0.0002869383,0.0004220436,0.000142477,0.001127361,0.0003962437,0.0006152476,0.0002811909,0.0008058278],"category_scores_gemma":[0.003352143,0.0002251498,0.0001945571,0.0014154,0.000592999,0.000415328,0.0001735598,0.0002646536,0.00001892143],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003055818,"about_ca_system_score_gemma":0.0006159208,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.07728375,"about_ca_topic_score_gemma":0.02695783,"domain_scores_codex":[0.9947898,0.002394556,0.001110807,0.0005164699,0.0007538666,0.0004345406],"domain_scores_gemma":[0.9957663,0.002143527,0.0005507696,0.0004913048,0.0009540099,0.00009411677],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002151159,0.001494303,0.4630763,0.0002356224,0.0004873687,4.738449e-7,0.01681906,0.00007945485,0.1364003,0.3605991,0.007651573,0.01294128],"study_design_scores_gemma":[0.002360373,0.0002619229,0.9241608,0.0002709558,0.0004440802,1.191251e-7,0.02408354,0.005246897,0.02711844,0.007219585,0.008086176,0.0007470579],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9262179,0.000397568,0.002429207,0.02202215,0.005448413,0.001785425,0.00008484557,0.0001410138,0.04147348],"genre_scores_gemma":[0.9825854,0.0003090357,0.0003265987,0.0003846992,0.0004093324,0.00006527746,0.00005396988,0.00001091664,0.01585472],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4610845,"threshold_uncertainty_score":0.9907976,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05532363522220222,"score_gpt":0.4307930285494517,"score_spread":0.3754693933272495,"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."}}