{"id":"W4410552381","doi":"10.1287/ijoc.2024.0645","title":"Mitigating Age-Related Bias in Large Language Models: Strategies for Responsible Artificial Intelligence Development","year":2025,"lang":"en","type":"article","venue":"INFORMS journal on computing","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning","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":[0.00211328,0.0001567581,0.0002775495,0.0005845081,0.0003976216,0.0001763838,0.0001299638,0.0001355713,0.00001909816],"category_scores_gemma":[0.0007533228,0.0001320298,0.0000895791,0.0005635529,0.00003803503,0.0002814477,0.0000376858,0.0006482489,0.00001870853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003265761,"about_ca_system_score_gemma":0.001708772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008270201,"about_ca_topic_score_gemma":0.0002158255,"domain_scores_codex":[0.997771,0.00004396758,0.001304527,0.0001769409,0.0002339577,0.0004696539],"domain_scores_gemma":[0.9986578,0.0005876059,0.0002611395,0.0001340953,0.0002481518,0.0001111977],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005025502,0.0002161121,0.00188498,0.0002238323,0.00005739456,0.00008554366,0.04376397,0.03885272,0.0004430005,0.07243314,0.00009457077,0.8414422],"study_design_scores_gemma":[0.000321256,0.0006264536,0.002213215,0.005695361,0.0000376736,0.000148375,0.1725253,0.5354936,0.04892519,0.2323311,0.001194151,0.0004882427],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9087614,0.0001753123,0.08605124,0.001235774,0.0007314266,0.0004082062,9.873171e-7,0.00005012196,0.002585572],"genre_scores_gemma":[0.9860985,0.0000141354,0.01255025,0.0009207774,0.0001842133,0.000009191765,0.00001362395,0.00001256815,0.0001967182],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8409539,"threshold_uncertainty_score":0.5384018,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2140609830821581,"score_gpt":0.4436225516661311,"score_spread":0.229561568583973,"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."}}