{"id":"W4401158708","doi":"10.21203/rs.3.rs-4670889/v1","title":"Addressing Gender Bias in Generative Large Language Models","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Generative grammar; Gender bias; Psychology; Cognitive psychology; Social psychology; Computer science; Artificial intelligence","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":[0.01796087,0.001165428,0.001912639,0.001364236,0.001334191,0.003038355,0.002154172,0.002923961,0.005169048],"category_scores_gemma":[0.0982917,0.001599603,0.001411521,0.001507756,0.001569496,0.005573648,0.003395,0.004414648,0.001253657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00153495,"about_ca_system_score_gemma":0.001754677,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005067316,"about_ca_topic_score_gemma":0.007652331,"domain_scores_codex":[0.9913419,0.006741853,0.0002069999,0.0008730657,0.0005134121,0.0003227607],"domain_scores_gemma":[0.8691313,0.1228001,0.0012934,0.004142158,0.001850535,0.0007825239],"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":[0.001420395,0.0003389249,0.02712269,0.0007545446,0.0009539871,0.0008326542,0.003472597,0.3143046,0.01036935,0.4289597,0.01699227,0.1944783],"study_design_scores_gemma":[0.00005692405,0.00003638188,0.0008886118,0.00003878257,0.00008461333,0.00008959879,0.0001142397,0.8187292,0.001635574,0.1767896,0.001515441,0.00002099893],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09778421,0.001650447,0.8910906,0.004217015,0.000305961,0.00007358135,0.0005987627,0.001106351,0.003172976],"genre_scores_gemma":[0.8945513,0.001231462,0.09306154,0.001370651,0.0009205234,0.0002160783,0.001505023,0.001314192,0.005829153],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01796087,"threshold_uncertainty_score":0.09498727,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4433290697922615,"score_gpt":0.4825964374306563,"score_spread":0.03926736763839483,"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."}}