{"id":"W4417093945","doi":"10.1016/j.emj.2025.12.002","title":"The ethics mirror? Comparing LLM and human responses to ethical dilemmas of varying complexity","year":2025,"lang":"en","type":"article","venue":"European Management Journal","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"European Regional Development Fund; Ministerio de Asuntos Económicos y Transformación Digital, Gobierno de España; European Commission","keywords":"Ethical dilemma; Business ethics; Normative; Agency (philosophy); Dilemma; Ethical issues; Ethical values; Applied ethics","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":[0.01326547,0.0004344654,0.0004020394,0.0005156278,0.0006603647,0.002602102,0.0006482432,0.001903844,0.004213919],"category_scores_gemma":[0.1167434,0.0003808002,0.0003280575,0.0002208482,0.00403984,0.002995179,0.003015429,0.001914943,0.0004863986],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008544189,"about_ca_system_score_gemma":0.0008452233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003275618,"about_ca_topic_score_gemma":0.0003897358,"domain_scores_codex":[0.9778807,0.01811545,0.0006318177,0.001102696,0.001836717,0.0004325679],"domain_scores_gemma":[0.9079006,0.07285924,0.008796216,0.00674583,0.001983047,0.001715173],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.01111722,0.005502427,0.1771463,0.0036842,0.0005367656,0.001456384,0.1681776,0.0382804,0.2319324,0.1228685,0.005036355,0.2342615],"study_design_scores_gemma":[0.001750311,0.0150437,0.2829077,0.001700372,0.0004162333,0.003099433,0.08140469,0.1329724,0.07749128,0.3511197,0.0511921,0.0009020491],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9612306,0.0001317313,0.01789042,0.001071638,0.00006718917,0.0002514036,0.00004730794,0.00009407221,0.0192155],"genre_scores_gemma":[0.9882598,0.00005423801,0.009988273,0.000674102,0.00001346076,0.0002759171,0.00004026427,0.00003396831,0.0006600072],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01326547,"threshold_uncertainty_score":0.07015532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2091869540923761,"score_gpt":0.4517723436148977,"score_spread":0.2425853895225216,"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."}}