{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.01518727,0.000094354,0.0001578868,0.0001224177,0.004708714,0.0006992025,0.0005591194,0.00007768855,0.00001732406],"category_scores_gemma":[0.001598456,0.00007638253,0.00006694138,0.0002535836,0.0007738256,0.0001026112,0.0004238366,0.001630434,0.000007732006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006243887,"about_ca_system_score_gemma":0.00007561125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003670383,"about_ca_topic_score_gemma":0.0008820276,"domain_scores_codex":[0.9958456,0.002756836,0.0003609236,0.00014339,0.0005820529,0.0003112436],"domain_scores_gemma":[0.9983951,0.0008893937,0.0001498201,0.0001608242,0.0002404842,0.0001643606],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004987195,0.00003157476,0.003371129,0.00003120856,0.00008088148,0.00002923,0.01552525,0.000003694947,0.00008174355,0.9763397,0.002442498,0.002013216],"study_design_scores_gemma":[0.0007767937,0.0001644418,0.2755245,0.0006357612,0.0001037137,0.000002695588,0.01784805,0.00002070112,0.00002655217,0.2183544,0.4862534,0.0002889698],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1933039,0.0001193951,0.0007650661,0.1184928,0.0004226559,0.0002276951,0.000001291552,0.00003785644,0.6866294],"genre_scores_gemma":[0.9916969,0.0004245791,0.001118827,0.003278884,0.0001030888,6.565006e-7,3.0898e-7,0.000009735084,0.003367052],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.798393,"threshold_uncertainty_score":0.996587,"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."}}