{"id":"W4409403219","doi":"10.1007/978-3-031-87766-7_22","title":"Gender and Race Bias in Consumer Product Recommendations by Large Language Models","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes on data engineering and communications technologies","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Race (biology); Product (mathematics); Psychology; Computer science; Sociology; Gender studies; Mathematics","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":[0.01098204,0.0005363796,0.0008630728,0.001054227,0.0006856354,0.00192911,0.001171954,0.001284048,0.004311682],"category_scores_gemma":[0.02998044,0.0006318583,0.001784099,0.001244834,0.001060007,0.003844165,0.0008483402,0.002425039,0.001148455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009140025,"about_ca_system_score_gemma":0.0005983661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01102355,"about_ca_topic_score_gemma":0.0173966,"domain_scores_codex":[0.9970707,0.002098131,0.00007579441,0.0004138232,0.0001984599,0.0001430207],"domain_scores_gemma":[0.9492047,0.04768049,0.0007836742,0.001415873,0.0006627356,0.000252516],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.003778704,0.000976685,0.2181206,0.000467978,0.00244397,0.000893336,0.003375021,0.2336207,0.0087086,0.08581904,0.02443172,0.4173637],"study_design_scores_gemma":[0.00004914066,0.0001087737,0.02242398,0.00007179311,0.0002603434,0.0001590038,0.0003599505,0.9053018,0.00167194,0.06764513,0.001891677,0.00005655969],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8031706,0.00365834,0.173857,0.004743071,0.0003034308,0.0000738323,0.00172812,0.0008276087,0.01163792],"genre_scores_gemma":[0.9719754,0.0005232785,0.01758323,0.0003268908,0.0002391879,0.00004559981,0.001031898,0.0001859987,0.00808854],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01102355,"threshold_uncertainty_score":0.05807924,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09907225529256185,"score_gpt":0.3587585533588921,"score_spread":0.2596862980663302,"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."}}