{"id":"W4392560653","doi":"10.1145/3649449","title":"Pre-Trained Language Models for Text Generation: A Survey","year":2024,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Topic Modeling","field":"Computer Science","cited_by":174,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"National Natural Science Foundation of China","keywords":"Computer science; Text generation; Key (lock); Artificial intelligence; Field (mathematics); Language model; Deep learning; Data science; Natural language processing; Machine learning","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.009030863,0.000651346,0.001528736,0.0002973376,0.0002120506,0.0007583152,0.003479381,0.0003639283,0.000004157618],"category_scores_gemma":[0.0009136006,0.0005548502,0.0005702195,0.0008385144,0.00002952519,0.000259356,0.001691301,0.000509194,0.00007439674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001505159,"about_ca_system_score_gemma":0.0005730558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003217937,"about_ca_topic_score_gemma":0.0002002267,"domain_scores_codex":[0.9942071,0.00216832,0.001068091,0.001494719,0.0004125314,0.000649235],"domain_scores_gemma":[0.9946353,0.002181826,0.0003633285,0.002480187,0.0002023179,0.0001370763],"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":[2.91938e-7,0.00001861553,0.000001670532,0.003370676,0.0001187775,0.00001206975,0.0004997335,0.001361689,2.720488e-7,0.001980495,0.00208044,0.9905553],"study_design_scores_gemma":[0.0001504817,0.00003950102,0.00001191088,0.002818099,0.0001532895,0.00003918413,0.000003057865,0.9388282,6.420392e-7,0.0009058429,0.05628977,0.0007600319],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.000008503945,0.4883835,0.5092753,0.00002594994,0.001239888,0.0006030232,0.00006351588,0.0003435143,0.00005682959],"genre_scores_gemma":[0.001176065,0.7551275,0.2373811,0.0001381726,0.002666949,0.0001606131,0.001125916,0.0002263861,0.001997264],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.9897952,"threshold_uncertainty_score":0.9996903,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1677638019158179,"score_gpt":0.3821377924828532,"score_spread":0.2143739905670353,"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."}}