{"id":"W3101190870","doi":"10.18653/v1/2020.blackboxnlp-1.3","title":"Examining the rhetorical capacities of neural language models","year":2020,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"Canadian Institute for Advanced Research","keywords":"Rhetorical question; Computer science; ENCODE; Rhetoric; Set (abstract data type); Linguistics; Transformer; Rhetorical device; Artificial intelligence; Natural language processing; Philosophy; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00007705883,0.00004738822,0.00007502746,0.00001051345,0.00003001895,0.00002748607,0.000519278,0.00001634628,0.00001159129],"category_scores_gemma":[0.00002337479,0.00002948517,0.00002297194,0.00009874348,0.00002865845,0.0001979411,0.0001780088,0.00007388587,0.00000355024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005086747,"about_ca_system_score_gemma":0.00001271958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006156051,"about_ca_topic_score_gemma":0.000001852354,"domain_scores_codex":[0.9994726,0.00002877474,0.0001137691,0.0001334217,0.0001514737,0.00009994104],"domain_scores_gemma":[0.9996184,0.00006911993,0.00002556029,0.0002328972,0.00001712858,0.00003685375],"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":[0.000004022864,0.00001502385,0.0003051999,0.00002979666,0.00001731143,0.00001641417,0.1017307,0.06064151,0.004909973,0.7876294,0.0009969752,0.04370367],"study_design_scores_gemma":[0.00004726139,0.00002052976,0.00003155954,0.000001700001,0.000001096055,0.00000216053,0.001254654,0.9963322,0.001226551,0.001005483,0.00003804054,0.00003873613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1834139,0.00007492376,0.8067136,0.002122842,0.00007551739,0.00003293142,3.103158e-7,0.00007749848,0.007488469],"genre_scores_gemma":[0.9775377,0.000001058031,0.0212741,0.0009859998,0.00006564773,0.000001676053,1.028515e-7,0.000002484109,0.0001312494],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9356907,"threshold_uncertainty_score":0.120237,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1303927045679519,"score_gpt":0.2600605528241967,"score_spread":0.1296678482562448,"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."}}