{"id":"W6891691587","doi":"10.48448/gyd1-w707","title":"Controllable Dialogue Simulation with In-context Learning","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Fluency; Annotation; Set (abstract data type); Training set; Code (set theory); Language model","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","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001639349,0.0003849261,0.0005159122,0.001946249,0.0004412187,0.000177707,0.0008062813,0.0001389557,0.009146382],"category_scores_gemma":[0.0005253287,0.0003385247,0.00003972269,0.002972884,0.0009117043,0.0003215314,0.0002533628,0.0008075488,0.001658006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008851769,"about_ca_system_score_gemma":0.001046865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002090077,"about_ca_topic_score_gemma":0.01513688,"domain_scores_codex":[0.9963468,0.0001897442,0.0003453091,0.0009796295,0.00136633,0.0007721636],"domain_scores_gemma":[0.9984557,0.0002264558,0.0005020631,0.0005407979,0.0001260904,0.0001488621],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000264551,0.0003360735,0.01797725,0.00005631024,0.0000711851,0.0001370201,0.001360283,0.9271142,0.001055633,0.003063982,0.02813976,0.02042369],"study_design_scores_gemma":[0.002583575,0.0003346716,0.000246924,0.000119893,0.00003576243,0.000007969538,0.001196089,0.288394,0.00001794806,0.0001343809,0.7062363,0.0006924749],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.00245571,0.00108061,0.001281044,0.0001284035,0.000521953,0.001592304,0.0001269193,0.001045173,0.9917679],"genre_scores_gemma":[0.7699246,0.000007353265,0.0008346077,0.0001646027,0.000189577,0.00005770139,0.0001879619,0.0007005433,0.2279331],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.7674689,"threshold_uncertainty_score":0.9999067,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0168143610667692,"score_gpt":0.2777211271516795,"score_spread":0.2609067660849103,"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."}}