MétaCan
Menu
Back to cohort
Record W4417093945 · doi:10.1016/j.emj.2025.12.002

The ethics mirror? Comparing LLM and human responses to ethical dilemmas of varying complexity

2025· article· en· W4417093945 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueEuropean Management Journal · 2025
Typearticle
Languageen
FieldSocial Sciences
TopicEthics and Social Impacts of AI
Canadian institutionsCarleton University
FundersEuropean Regional Development FundMinisterio de Asuntos Económicos y Transformación Digital, Gobierno de EspañaEuropean Commission
KeywordsEthical dilemmaBusiness ethicsNormativeAgency (philosophy)DilemmaEthical issuesEthical valuesApplied ethics

Abstract

fetched live from OpenAlex

The rise of large language models (LLMs) such as GPT has increased their use in business settings, yet uncertainty persists regarding their integration, particularly when facing ethical dilemmas traditionally managed by humans. To investigate how closely LLMs mimic human responses in real-world business ethical challenges, we conduct three experiments. We present ethical dilemmas of varying complexity and focus, and we assess the effect of a specific prompt – consequence enumeration – on eliciting ethical responses from GPT versus humans. Findings indicate that GPT alone is more ethical than humans in less complex dilemmas where unethical behavior admits a clear normative response, while both GPT and human responses are similarly (un)ethical in more complex dilemmas. The impact of consequence enumeration on curbing unethical responses varies between GPT and humans, depending on dilemma complexity and focus. These insights advance research on AI ethics and its applications in business, offering strategies to address ethical challenges and boost human agency in LLM-driven decision-making as AI becomes increasingly prevalent in business and society.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.015
metaresearch head score (Gemma)0.002
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesScience and technology studies
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.798
Threshold uncertainty score0.997

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0150.002
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0050.001
Scholarly communication0.0010.000
Open science0.0010.000
Research integrity0.0000.002
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.209
GPT teacher head0.452
Teacher spread0.243 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it