{"id":"W4410004709","doi":"10.21449/ijate.1602294","title":"A review of automatic item generation techniques leveraging large language models","year":2025,"lang":"en","type":"review","venue":"International Journal of Assessment Tools in Education","topic":"Topic Modeling","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Natural language processing; Data science","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":[0.001635015,0.0002077572,0.0008400228,0.000914934,0.00002004316,0.0001573619,0.001522965,0.0001061404,0.00001869562],"category_scores_gemma":[0.000308082,0.0001842293,0.0003067066,0.0003668668,0.000008141082,0.001161075,0.0002017926,0.00038832,8.346465e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008648163,"about_ca_system_score_gemma":0.003529035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001111918,"about_ca_topic_score_gemma":0.000001990696,"domain_scores_codex":[0.9969439,0.0003031906,0.001711152,0.0002412826,0.0006693978,0.000131104],"domain_scores_gemma":[0.9967942,0.0002792411,0.001803099,0.0003757625,0.0007112435,0.00003644773],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[2.184027e-7,0.0001757594,0.00000391296,0.01473308,0.00006589167,0.000004746642,0.0001444262,0.00002694609,0.000002633165,0.008879484,0.0007667648,0.9751961],"study_design_scores_gemma":[0.0002530353,0.00005357057,0.00001461617,0.7045194,0.0002617082,0.0002154697,0.0001047624,0.0517667,0.00003102345,0.002479907,0.2398812,0.0004185924],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000008662538,0.6902927,0.3068741,0.0002738699,0.001503751,0.0003276632,0.000005881699,0.00001576116,0.0006976093],"genre_scores_gemma":[0.0001889932,0.8840411,0.1148644,0.0003720572,0.0003522904,0.00006228051,0.00005200467,0.000009553406,0.00005724613],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9747775,"threshold_uncertainty_score":0.7512653,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07488583176221998,"score_gpt":0.4522201303716182,"score_spread":0.3773342986093982,"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."}}