{"id":"W4394580931","doi":"10.35542/osf.io/6d8tj","title":"A Review of Automatic Item Generation Techniques Leveraging Large Language Models","year":2024,"lang":"en","type":"review","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Natural language processing; Language model; Data science; Artificial intelligence","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":[0.0008708113,0.0002931495,0.001168568,0.0002304815,0.00002891839,0.00009703993,0.0008887303,0.0001306318,0.0000297337],"category_scores_gemma":[0.00003914371,0.0002069369,0.0003853347,0.0004707106,0.000006563543,0.0003077491,0.0004633507,0.0002444149,0.00003710078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009131459,"about_ca_system_score_gemma":0.0002328418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001430299,"about_ca_topic_score_gemma":0.00000182906,"domain_scores_codex":[0.9979791,0.0001482264,0.0008714556,0.0005125055,0.0002764407,0.0002122723],"domain_scores_gemma":[0.9985905,0.00005200384,0.0002600052,0.0009970354,0.00005769342,0.00004280801],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[3.841787e-9,0.00000598333,2.315766e-9,0.1952165,0.0000199829,0.000005386839,0.00008680098,5.53492e-7,3.751953e-7,0.01374381,0.001958689,0.7889619],"study_design_scores_gemma":[0.00001015627,0.000005370768,6.963435e-10,0.2302028,0.0001976337,0.00003231473,0.000001889292,0.39007,0.000005711801,0.0003002475,0.3789812,0.0001927776],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[2.461839e-8,0.5480282,0.4499108,0.00003325249,0.00009914286,0.0004106866,0.000003293475,0.0003584617,0.001156095],"genre_scores_gemma":[9.125376e-7,0.8737669,0.1251615,0.0003583926,0.0001118103,0.0001134404,0.00002072117,0.00002382779,0.0004425039],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7887691,"threshold_uncertainty_score":0.8438643,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1025841590571828,"score_gpt":0.3687607373528912,"score_spread":0.2661765782957084,"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."}}