{"id":"W4393156935","doi":"10.1609/aaai.v38i21.30353","title":"How Teachers Can Use Large Language Models and Bloom’s Taxonomy to Create Educational Quizzes","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Canadian Institute for Advanced Research","funders":"Mitacs; Canadian Institute for Advanced Research","keywords":"Bloom; Taxonomy (biology); Bloom's taxonomy; Computer science; Mathematics education; Psychology; Biology; Ecology","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003154349,0.0001732477,0.0001661342,0.0001617294,0.0001354784,0.001235208,0.0008210025,0.00005552471,0.0000128532],"category_scores_gemma":[0.0003405839,0.0001299897,0.00006891497,0.000478797,0.000100264,0.000573512,0.00028872,0.0002783211,0.00001803134],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003509871,"about_ca_system_score_gemma":0.0001450581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009282819,"about_ca_topic_score_gemma":0.00004412993,"domain_scores_codex":[0.9987499,0.00001447811,0.0002188063,0.0004541209,0.0002839139,0.0002787626],"domain_scores_gemma":[0.9992449,0.0001162137,0.00008895894,0.0001944737,0.0002318385,0.0001235647],"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":[0.000005723299,0.00006500267,0.0003659137,0.0000333511,0.00001952324,7.726655e-7,0.005010194,0.0001308131,0.004110453,0.9545902,0.0003723747,0.03529566],"study_design_scores_gemma":[0.00003715523,0.0002365782,0.0003469245,0.0007566865,0.00004806718,0.00001445444,0.004385353,0.7542728,0.0652464,0.1697804,0.004324963,0.0005502093],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7829818,0.0002081323,0.06208293,0.1497188,0.0005940762,0.0007633447,0.00004383162,0.000277,0.003330158],"genre_scores_gemma":[0.9889646,0.00002475091,0.006816335,0.0002909276,0.000106326,0.00003876866,9.155261e-7,0.00001121372,0.003746125],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7848098,"threshold_uncertainty_score":0.9998016,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0861660931787799,"score_gpt":0.310739476438149,"score_spread":0.2245733832593691,"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."}}