{"id":"W4386566992","doi":"10.18653/v1/2023.c3nlp-1.8","title":"Toward Cultural Bias Evaluation Datasets: The Case of Bengali Gender, Religious, and National Identity","year":2023,"lang":"en","type":"article","venue":"","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Bengali; Unavailability; Nationality; Artifact (error); Identity (music); Process (computing); Cultural identity; Computer science; Natural language processing; Artificial intelligence; Psychology; Social psychology; Political science; Statistics; Mathematics; Immigration; Aesthetics","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":[],"consensus_categories":[],"category_scores_codex":[0.001485265,0.00005895631,0.00005566616,0.00006940976,0.0001579663,0.0001404318,0.0002196485,0.00002962123,0.00001495566],"category_scores_gemma":[0.0002430507,0.00003861061,0.00002531105,0.0004821797,0.00003611125,0.000646786,0.0001612711,0.0000620359,0.00004163131],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002601576,"about_ca_system_score_gemma":0.00005408833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007005462,"about_ca_topic_score_gemma":0.0002731793,"domain_scores_codex":[0.9990429,0.0001122837,0.0001454616,0.0001879192,0.0004079827,0.0001034139],"domain_scores_gemma":[0.9994388,0.00007981066,0.00005743189,0.0002013915,0.0001897143,0.00003285451],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002758533,0.0001317975,0.001485534,0.0001548755,0.0002199354,0.0004833733,0.01278791,0.001929472,0.008119924,0.3761977,0.4336762,0.1647857],"study_design_scores_gemma":[0.001117165,0.0001364523,0.01025722,0.0000210504,0.00006264449,0.002875773,0.00298619,0.8451951,0.009885492,0.1207768,0.006276121,0.0004100301],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9734565,0.0002775119,0.02145083,0.001751683,0.0005196571,0.0003828402,0.00008275696,0.0002560964,0.001822134],"genre_scores_gemma":[0.9982578,0.0001005077,0.001376494,0.0001072723,0.00003755667,0.0000113882,0.00006489608,0.000002321407,0.00004180421],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8432656,"threshold_uncertainty_score":0.1574495,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1445624502315244,"score_gpt":0.3546193864170398,"score_spread":0.2100569361855153,"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."}}