The ethics mirror? Comparing LLM and human responses to ethical dilemmas of varying complexity
Bibliographic record
Abstract
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.013 | 0.117 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.004 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".