{"id":"W4382567310","doi":"10.1007/978-3-031-36336-8_83","title":"How Useful Are Educational Questions Generated by Large Language Models?","year":2023,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Topic Modeling","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; Canadian Institute for International Peace and Security; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Quality (philosophy); Domain (mathematical analysis); Mathematics education; Natural language processing; Psychology; Epistemology; Mathematics","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007768901,0.000219398,0.0002139446,0.0008326467,0.0005777803,0.00129405,0.003225552,0.000139831,0.000004508299],"category_scores_gemma":[0.00006093826,0.0002313362,0.0000419948,0.0005471669,0.0003182832,0.008399913,0.002176347,0.0004349054,0.00006095345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001617603,"about_ca_system_score_gemma":0.0003710765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001794131,"about_ca_topic_score_gemma":0.00003179202,"domain_scores_codex":[0.9983382,0.00003564204,0.0004835211,0.0003599448,0.0004985827,0.000284077],"domain_scores_gemma":[0.996699,0.0001648865,0.0003288083,0.002241116,0.000442765,0.000123423],"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":[3.315142e-7,0.00001656106,0.00002233412,0.00001604844,0.000004728902,2.761203e-7,0.001701333,0.001101159,0.000005187305,0.9729417,0.002077938,0.02211238],"study_design_scores_gemma":[0.0001598716,0.000009401692,0.0002356202,0.0001335478,0.000003324061,0.000009431275,0.00005640636,0.9355635,0.000004375368,0.02021181,0.04333968,0.0002730376],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00008460377,0.0006938516,0.9505878,0.009601752,0.0004612394,0.000322355,0.00009504582,0.000228507,0.03792483],"genre_scores_gemma":[0.2229266,0.01018271,0.6703973,0.007217496,0.0004350277,0.0003472164,0.001667532,0.00009387036,0.08673226],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9527299,"threshold_uncertainty_score":0.9997427,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05845123054466652,"score_gpt":0.2962198031426312,"score_spread":0.2377685725979647,"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."}}