{"id":"W4403988122","doi":"10.15837/ijccc.2024.6.6853","title":"Evaluating and Mitigating Gender Bias in Generative Large Language Models","year":2024,"lang":"en","type":"article","venue":"International Journal of Computers Communications & Control","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Generative grammar; Natural language processing; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001469799,0.00012446,0.000194853,0.0004980984,0.00007812431,0.0005890749,0.002259911,0.00004950654,0.00000267398],"category_scores_gemma":[0.000174275,0.0001090781,0.00008432391,0.0002471721,0.00005518598,0.001265792,0.0005601838,0.0004803571,0.000001497071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000135154,"about_ca_system_score_gemma":0.0001582191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001697751,"about_ca_topic_score_gemma":0.00001340352,"domain_scores_codex":[0.998349,0.0003244327,0.0005520612,0.0001747842,0.00044697,0.0001527836],"domain_scores_gemma":[0.9979613,0.000847267,0.0002549721,0.0004203733,0.0004603878,0.00005572484],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000269849,0.000164508,0.0004635757,0.00003273797,0.0003974404,0.0002645684,0.02015081,0.0043176,0.009564594,0.5907232,0.0003814356,0.3735125],"study_design_scores_gemma":[0.0006253267,0.00004046795,0.00009653742,0.0003269711,0.00001167586,0.0002269547,0.0001231373,0.9429747,0.0003266057,0.05498204,0.0001588764,0.0001067153],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01323104,0.02544981,0.9547515,0.005828064,0.0003808253,0.0001124027,0.000007196373,0.00009672163,0.0001424365],"genre_scores_gemma":[0.5856295,0.0001040505,0.4136823,0.0004936526,0.00007135344,0.000005245381,0.000002251607,0.000006247245,0.000005477422],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9386571,"threshold_uncertainty_score":0.5680463,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08070041347036223,"score_gpt":0.3999135031773028,"score_spread":0.3192130897069406,"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."}}