{"id":"W4385571912","doi":"10.18653/v1/2023.findings-acl.356","title":"LABO: Towards Learning Optimal Label Regularization via Bi-level Optimization","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Université de Montréal; Huawei Technologies (Canada)","funders":"","keywords":"Regularization (linguistics); Computer science; Smoothing; Artificial intelligence; Normalization (sociology); Machine learning; Deep neural networks; Artificial neural network; Mathematical optimization; Mathematics","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":[0.004518323,0.00174883,0.001924875,0.001059084,0.000799531,0.002096937,0.002588566,0.002969318,0.00316866],"category_scores_gemma":[0.01008191,0.001106026,0.00116801,0.001295476,0.002101357,0.003157752,0.003974278,0.005126246,0.002145552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001569331,"about_ca_system_score_gemma":0.002679292,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00365876,"about_ca_topic_score_gemma":0.005026544,"domain_scores_codex":[0.9980317,0.0007649652,0.00008564846,0.0003742689,0.000561256,0.0001822602],"domain_scores_gemma":[0.9970254,0.001541666,0.0002683548,0.0004887864,0.0005020901,0.0001737638],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002457226,0.0003230863,0.001444455,0.0002585519,0.0001144744,0.00009165944,0.0002305201,0.6984917,0.006620291,0.06715603,0.01595231,0.2090711],"study_design_scores_gemma":[0.000008170857,0.0000133611,0.00003413914,0.000007594396,0.000002967427,0.000005727049,0.000006002091,0.9875295,0.0004935314,0.01133417,0.0005597515,0.000005052671],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002891597,0.0001015836,0.9949698,0.000234634,0.0000271413,0.0000345479,0.0000397166,0.000913958,0.000786954],"genre_scores_gemma":[0.145333,0.0002134763,0.8464967,0.0008886873,0.00013018,0.0004483581,0.0005585484,0.001260686,0.004670409],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004518323,"threshold_uncertainty_score":0.02389544,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03958658749458459,"score_gpt":0.2820888890739697,"score_spread":0.2425023015793851,"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."}}