{"id":"W4402669930","doi":"10.18653/v1/2024.repl4nlp-1.4","title":"Learning from Others: Similarity-based Regularization for Mitigating Dataset Bias.","year":2024,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Azrieli Foundation; Open Philanthropy Project","keywords":"Regularization (linguistics); Computer science; Similarity (geometry); Artificial intelligence; Machine learning; Pattern recognition (psychology)","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":[0.005995181,0.001429381,0.001496255,0.001526839,0.0009714859,0.001343807,0.003098737,0.002650021,0.001261516],"category_scores_gemma":[0.01971979,0.0005706814,0.001304207,0.001316787,0.002124346,0.003103027,0.004323107,0.00370564,0.0007082182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001001015,"about_ca_system_score_gemma":0.001143905,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002062413,"about_ca_topic_score_gemma":0.003728687,"domain_scores_codex":[0.9967307,0.001524291,0.0001495268,0.0008198307,0.0006012089,0.0001745149],"domain_scores_gemma":[0.9911032,0.004472863,0.0008406614,0.0024608,0.00074263,0.000379813],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007405507,0.0007614876,0.01264588,0.0005753226,0.0007827969,0.0003249672,0.0009061156,0.3285354,0.02727499,0.02897996,0.01826007,0.5802125],"study_design_scores_gemma":[0.00002854644,0.0001193608,0.0007957047,0.00002559531,0.00004422316,0.0001111349,0.0000445962,0.9719431,0.004850235,0.02046603,0.00154638,0.00002502157],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04534814,0.001025163,0.9492502,0.0006073146,0.00009152698,0.0001233417,0.0002130686,0.002145955,0.001195343],"genre_scores_gemma":[0.6096964,0.0004534109,0.3819809,0.001387392,0.0002917396,0.0003454672,0.001651425,0.0005424036,0.003650836],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005995181,"threshold_uncertainty_score":0.03170592,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05805738761050586,"score_gpt":0.2891870858740692,"score_spread":0.2311296982635633,"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."}}