{"id":"W4405368118","doi":"10.31234/osf.io/t9x8r","title":"Moral Stereotyping in Large Language Models","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Globe; Stereotype (UML); Social psychology; Psychology; Sociology; Positive economics; Economics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003456516,0.0001902654,0.0002012301,0.0002953494,0.00002832321,0.0003897929,0.0007072894,0.0002006783,0.00003160901],"category_scores_gemma":[0.000006913161,0.0001746748,0.00009917267,0.0002620246,0.000007419727,0.0001670782,0.00261507,0.0008099114,0.0002761715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008807053,"about_ca_system_score_gemma":0.0001013014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004249818,"about_ca_topic_score_gemma":0.0003459933,"domain_scores_codex":[0.9985691,0.00004844687,0.0002310418,0.0006083056,0.0002051803,0.0003379031],"domain_scores_gemma":[0.9992029,0.00001362943,0.00004121881,0.0006592052,0.00002169912,0.00006132587],"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":[0.00001397053,0.0001828979,0.0001664422,0.0008150708,0.00009435175,0.001193558,0.01330696,0.01915179,0.0005222359,0.8138335,0.002439446,0.1482797],"study_design_scores_gemma":[0.00011882,0.00001293071,0.00004918336,0.0002087898,0.000004178075,0.00001046956,0.00009695728,0.8090248,0.0009319367,0.189101,0.0001811491,0.0002598114],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1428604,0.001906362,0.7228302,0.001082311,0.003320255,0.0005164321,0.00001597169,0.00159862,0.1258694],"genre_scores_gemma":[0.9770343,0.00002262532,0.01859237,0.0002215412,0.0001144759,0.00003225659,0.000007884123,0.00001787265,0.003956695],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8341739,"threshold_uncertainty_score":0.7123032,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02241511617094059,"score_gpt":0.2629222091736161,"score_spread":0.2405070930026756,"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."}}