{"id":"W4381551981","doi":"10.48550/arxiv.2306.10414","title":"KEST: Kernel Distance Based Efficient Self-Training for Improving Controllable Text Generation","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Text generation; Fluency; Bottleneck; Generator (circuit theory); Natural language generation; Exploit; Kernel (algebra); Language model; Artificial intelligence; Process (computing); Machine learning; Natural language; Mathematics; Power (physics)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001738919,0.001105157,0.0008894412,0.0008340485,0.0004702478,0.0007261283,0.001914317,0.001243451,0.002951685],"category_scores_gemma":[0.007484374,0.0004912794,0.0007807267,0.0006625165,0.0009139851,0.002338235,0.002136535,0.001906517,0.001837303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006344428,"about_ca_system_score_gemma":0.000874636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001924261,"about_ca_topic_score_gemma":0.003336864,"domain_scores_codex":[0.9990304,0.0003590602,0.00006432053,0.0002614142,0.0002020812,0.00008274372],"domain_scores_gemma":[0.9966899,0.001987631,0.0002156871,0.0005438579,0.000429119,0.0001337966],"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":[0.0004101269,0.0003624871,0.002065441,0.0002451712,0.00009956765,0.0001851878,0.0004174887,0.4143884,0.0234859,0.01076202,0.008553194,0.5390249],"study_design_scores_gemma":[0.00001432068,0.00004602449,0.0001104774,0.000005536383,0.00000526863,0.0000285965,0.00001279165,0.9923701,0.003688579,0.003075072,0.0006358239,0.00000733551],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02753972,0.0003181612,0.9653747,0.000127179,0.00006615158,0.00006806329,0.0001068509,0.005284325,0.001114904],"genre_scores_gemma":[0.5855445,0.0002604814,0.4024695,0.000430917,0.0001005753,0.0003362508,0.001656913,0.001564332,0.007636534],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002951685,"threshold_uncertainty_score":0.009874344,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1131849059198157,"score_gpt":0.2004997923629383,"score_spread":0.0873148864431226,"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."}}