{"id":"W4286506316","doi":"10.3233/faia220062","title":"Few-Shot Question Generation for Personalized Feedback in Intelligent Tutoring Systems","year":2022,"lang":"en","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; McGill University","funders":"","keywords":"Computer science; Generative grammar; Artificial intelligence; Transformer; Question answering; Natural language processing; Ranking (information retrieval); Similarity (geometry); Generative model; Natural language generation; Natural language; Machine learning; Engineering","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":[0.001654804,0.0009715799,0.0007586151,0.0005612615,0.0003418261,0.0008432412,0.001964725,0.001468337,0.004530709],"category_scores_gemma":[0.006405317,0.0003511087,0.00056658,0.0003812835,0.000408464,0.001534719,0.0009312286,0.001391097,0.001878178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007424665,"about_ca_system_score_gemma":0.0005282802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001741742,"about_ca_topic_score_gemma":0.00277617,"domain_scores_codex":[0.9989654,0.000532253,0.00004392411,0.0002501082,0.0001654409,0.00004291692],"domain_scores_gemma":[0.9971032,0.002175111,0.00008415496,0.0002418663,0.000314107,0.0000815028],"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":[0.0004288105,0.0003680399,0.001728598,0.0006841671,0.00007321958,0.0002958094,0.0009245452,0.1303786,0.03779465,0.008339162,0.01221434,0.8067701],"study_design_scores_gemma":[0.00003818767,0.000208522,0.0006210841,0.00003134579,0.00003846678,0.0001708669,0.000078137,0.9564029,0.02144359,0.01357425,0.00736437,0.0000282759],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03563937,0.001602843,0.9473788,0.0003414229,0.0001173551,0.0001900825,0.0002744561,0.01206028,0.002395389],"genre_scores_gemma":[0.4891656,0.0005881983,0.4990235,0.0002965966,0.000100113,0.0002681953,0.001297504,0.0007048192,0.008555415],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004530709,"threshold_uncertainty_score":0.01515669,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08698854896693997,"score_gpt":0.2978302649463502,"score_spread":0.2108417159794102,"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."}}