{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003539851,0.0002786074,0.0003461535,0.001000428,0.0001518745,0.001013361,0.001733481,0.0003618594,0.00004436455],"category_scores_gemma":[0.0002072863,0.0002568084,0.0001435579,0.0007645798,0.00005041472,0.0003192592,0.009246381,0.003299696,0.0001479309],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004648445,"about_ca_system_score_gemma":0.0008902776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003485388,"about_ca_topic_score_gemma":0.0002792447,"domain_scores_codex":[0.9948541,0.0009067494,0.0003975749,0.001337061,0.001496808,0.001007712],"domain_scores_gemma":[0.9977006,0.0002075549,0.00005493307,0.001579136,0.0002812125,0.0001765497],"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":[0.00002207271,0.0003349059,0.0003938976,0.004593679,0.0001398864,0.003838296,0.1039356,0.1948744,0.0009392768,0.6418923,0.005538639,0.04349709],"study_design_scores_gemma":[0.0001423667,0.00001601681,0.00006108865,0.0008691546,0.000002103061,0.000006543332,0.0006990757,0.829082,0.0003606747,0.168346,0.0001793884,0.0002355402],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1024095,0.02361795,0.8422094,0.003099134,0.001238186,0.001790491,0.0001442444,0.0006287983,0.0248623],"genre_scores_gemma":[0.9670841,0.0001590294,0.0304921,0.00007635784,0.0004754096,0.0002187057,0.00003199211,0.00004616728,0.001416197],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8646746,"threshold_uncertainty_score":0.9999884,"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."}}