{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01755542,0.00225258,0.003062878,0.01065265,0.00052806,0.002730724,0.002612467,0.001297042,0.004696497],"category_scores_gemma":[0.06382826,0.001179525,0.003354053,0.008911084,0.0008310736,0.004513082,0.001342273,0.001481896,0.002666786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001147437,"about_ca_system_score_gemma":0.004008513,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003400883,"about_ca_topic_score_gemma":0.004948286,"domain_scores_codex":[0.9903853,0.005451645,0.001315812,0.0008204722,0.001901669,0.0001251643],"domain_scores_gemma":[0.9077246,0.0834993,0.002517563,0.001554414,0.004466215,0.0002378525],"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":[0.00007061646,0.00008498618,0.0009808944,0.04985424,0.0005192439,0.00005751894,0.0003002257,0.001150876,0.0003316297,0.00156384,0.005723718,0.9393622],"study_design_scores_gemma":[0.0003185026,0.001398328,0.02667657,0.1894797,0.00941641,0.002734108,0.00172687,0.01924842,0.005946143,0.02628515,0.7161906,0.000579092],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001354571,0.9732526,0.02172538,0.0007793853,0.0002198762,0.0002710902,0.0003009002,0.00032982,0.001766393],"genre_scores_gemma":[0.02001863,0.9077151,0.06840263,0.0007257974,0.0004520812,0.0008182878,0.0009832553,0.0001278529,0.0007563382],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.01755542,"threshold_uncertainty_score":0.092843,"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."}}