{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007975264,0.0009348873,0.0005148005,0.001467733,0.0005959288,0.004392666,0.001477697,0.001440801,0.003644048],"category_scores_gemma":[0.03549257,0.0006019343,0.0008892997,0.0007012422,0.001188147,0.007705117,0.001812378,0.001523508,0.001989995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001590513,"about_ca_system_score_gemma":0.001870618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004632994,"about_ca_topic_score_gemma":0.007489019,"domain_scores_codex":[0.9944189,0.003363345,0.0004391863,0.0007978763,0.0008156904,0.0001650844],"domain_scores_gemma":[0.9814566,0.0139226,0.0009816141,0.001632993,0.001665459,0.0003407014],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005000732,0.0008152988,0.02190165,0.001215124,0.000126096,0.0006795375,0.017636,0.05304242,0.02057592,0.1717609,0.02687289,0.6848741],"study_design_scores_gemma":[0.0002549204,0.0004818013,0.007363599,0.0005679501,0.0001161844,0.0009345156,0.006067174,0.5107967,0.02819027,0.3173438,0.1276341,0.0002489273],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06725364,0.000349239,0.9063112,0.003055964,0.00009617912,0.000863643,0.000588364,0.006445988,0.01503577],"genre_scores_gemma":[0.3134431,0.0002177092,0.6800696,0.0004012049,0.0000184453,0.0004781224,0.0009151868,0.0004491137,0.00400737],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007975264,"threshold_uncertainty_score":0.04217774,"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."}}