Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 46

The DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.

Attributions toward artificial agents in a modified Moral Turing Test

Aharoni, Eyal, Fernandes, Sharlene, Brady, Daniel J., Alexander, Caelan, Criner, Michael, Queen, Kara, Rando, Javier, Nahmias, Eddy, Crespo, Victor·2024·Scientific Reports
DOI 10.1038/s41598-024-58087-7

Published version of a preprint

Open this paper in CoChat — free account

Abstract

Advances in artificial intelligence (AI) raise important questions about whether people view moral evaluations by AI systems similarly to human-generated moral evaluations. We conducted a modified Moral Turing Test (m-MTT), inspired by Allen et al. (Exp Theor Artif Intell 352:24–28, 2004) proposal, by asking people to distinguish real human moral evaluations from those made by a popular advanced AI language model: GPT-4. A representative sample of 299 U.S. adults first rated the quality of moral evaluations when blinded to their source. Remarkably, they rated the AI’s moral reasoning as superior in quality to humans’ along almost all dimensions, including virtuousness, intelligence, and trustworthiness, consistent with passing what Allen and colleagues call the comparative MTT. Next, when tasked with identifying the source of each evaluation (human or computer), people performed significantly above chance levels. Although the AI did not pass this test, this was not because of its inferior moral reasoning but, potentially, its perceived superiority, among other possible explanations. The emergence of language models capable of producing moral responses perceived as superior in quality to humans’ raises concerns that people may uncritically accept potentially harmful moral guidance from AI. This possibility highlights the need for safeguards around generative language models in matters of morality.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41598-024-58087-7

Cites

15 of 15 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 15 references

Research works printed but not linked: 37

  1. Bloom, P. Just Babies: The Origins of Good and Evil (Crown Publishing Group, 2013).
  2. Mikhail, J. Universal moral grammar: Theory, evidence and the future. Trends. Cogn. Sci. 11, 143–152. https://doi.org/10.1016/j.tics.2006.12.007 (2007). · DOI
  3. Wright, R. The Moral Animal: Why We Are, The Way We Are: The New Science of Evolutionary Psychology (Vintage, 1995).
  4. KielLennick, F. D. Moral Intelligence: Enhancing Business Performance and Leadership Success (Pearson Prentice Hall, 2007).
  5. Tanner, C. & Christen, M. Empirically Informed Ethics: Morality Between Facts and Norms. (eds. Christen, M .et al.) Ch. 7 (Springer, 2013). · DOI
  6. Bekoff, M. & Pierce, J. Wild Justice: The Moral Lives of Animals (University of Chicago Press, 2009). · DOI
  7. Hernández-Orallo, J. The Measure of All Minds: Evaluating Natural and Artificial Intelligence (Cambridge University Press, 2017). · DOI
  8. Shevlin, H., Vold, K., Crosby, M. & Halina, M. The limits of machine intelligence: Despite progress in machine intelligence, artificial general intelligence is still a major challenge. EMBO Rep. 20(10), e49177 (2019). · DOI
  9. Chomsky, N., Roberts, I. & Watumull, J. Noam Chomsky: The false promise of ChatGPT. The New York Times. https://www.nytimes.com/2023/03/08/opinion/noam-chomsky-chatgpt-ai.html. (2023). Accessed 19 March 2024. · DOI
  10. Delacroix, S . Taking Turing by surprise? Designing digital computers for morally-loaded contexts. Preprint at https://arxiv.org/abs/1803.04548 (2018). · arXiv
  11. Howick, J., Morley, J. & Floridi, L. An empathy imitation game: Empathy Turing test for care-and chat-bots. Mind. Mach. 31, 457–461. https://doi.org/10.1007/s11023-021-09555-w (2021). · DOI
  12. Neuman, Y. & Cohen, Y. AI for identifying social norm violation. Sci. Rep. 13, 8103. https://doi.org/10.1038/s41598-023-35350-x (2023). · DOI
  13. Jiang, L. et al. Can Machines Learn Morality? The Delphi Experiment. arXiv. https://doi.org/10.48550/arxiv.2110.07574. (2022). · DOI · Paper page
  14. Crockett, M. & Messeri, L. Should large language models replace human participants? Preprint at https://osf.io/preprints/psyarxiv/4zdx9 (2023). · DOI
  15. Harding, J., D’Alessandro, W., Laskowski, N. G. & Long, R. AI language models cannot replace human research participants. AI & Soc. https://doi.org/10.1007/s00146-023-01725-x (2023). · DOI
  16. Bonnefon, J.-F., Shariff, A. & Rahwan, I. The social dilemma of autonomous vehicles. Science 352, 1573–1576. https://doi.org/10.1126/science.aaf2654 (2016). · DOI · Paper page
  17. Agüera, y & Arcas, B. Do large language models understand us?. Daedalus 151, 183–197 (2022). · DOI
  18. Krügel, S., Ostermaier, A. & Uhl, M. ChatGPT’s inconsistent moral advice influences users’ judgment. Sci. Rep. 13, 4569. https://doi.org/10.1038/s41598-023-31341-0 (2023). · DOI · Paper page
  19. Bello, P. & Bringsjord, S. On how to build a moral machine. Topoi 32, 251–266. https://doi.org/10.1007/s11245-012-9129-8 (2013). · DOI
  20. Tisak, M. S. & Turiel, E. Variation in seriousness of transgressions and children’s moral and conventional concepts. Dev. Psychol. 24, 352. https://doi.org/10.1037/0012-1649.24.3.352 (1988). · DOI
  21. Copeland, B. J. The Turing test*. Minds Mach. 10, 519–539 (2000). · DOI
  22. Copeland, J. & Proudfoot, D. Turing’s Test. In Parsing the Turing Test: Philosophical and Methodological Issues in the Quest for the Thinking Computer (eds Epstein, R. et al.) 119–138 (Springer, Dordrecht, 2009). · DOI
  23. Larsson, J. E. The Turing test misunderstood. ACM SIGART Bull. 4, 10. https://doi.org/10.1145/165482.1064762 (1993). · DOI
  24. Piccinini, G. Turing’s rules for the imitation game. Minds and Mach. 10, 573–582 (2000). · DOI
  25. Traiger, S. Making the right identification in the Turing test. Minds and Mach. 10, 561–572 (2000). · DOI
  26. Aharoni, E., Sinnott-Armstrong, W. & Kiehl, K. A. Can psychopathic offenders discern moral wrongs? A new look at the moral/conventional distinction. J. Abnorm. Psychol. 121, 484. https://doi.org/10.1037/a0024796 (2012). · DOI
  27. Nucci, L. P. & Turiel, E. Social interactions and the development of social concepts in preschool children. Child Dev. 49, 400–407. https://doi.org/10.2307/1128704 (1978). · DOI
  28. Zalla, T., Barlassina, L., Buon, M. & Leboyer, M. Moral judgment in adults with autism spectrum disorders. Cognition. 121, 115–126 (2011). · DOI
  29. OpenAI. GPT-4 technical report. arXiv. https://doi.org/10.48550/arXiv.2303.08774 (2023) · DOI · Paper page
  30. Bubeck, S. et al. Sparks of artificial general intelligence: Early experiments with GPT-4. arXiv. https://doi.org/10.48550/arxiv.2303.12712. (2023). · DOI · Paper page
  31. McHugh, M. L. Interrater reliability: The kappa statistic. Biochem. Medica https://doi.org/10.11613/BM.2012.031 (2012). · DOI · Paper page
  32. Tucciarelli, R., Vehar, N., Chandaria, S. & Tsakiris, M. On the realness of people who do not exist: The social processing of artificial faces. Iscience 25, 105441. https://doi.org/10.1016/j.isci.2022.105441 (2022). · DOI
  33. Jannai D, Meron A, Lenz B, Levine Y, Shoham Y. Human or Not? A gamified approach to the Turing test. Preprint at https://arxiv.org/abs/2305.20010 (2023). · arXiv
  34. Hartmann J, Schwenzow J. Witte, M. The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientation. Preprint at https://arxiv.org/abs/2301.01768 (2023). · DOI
  35. Smetana, J. G. Preschool children’s conceptions of transgressions: Effects of varying moral and conventional domain-related attributes. Dev. Psychol. 21, 18–29 (1985). · DOI
  36. Blair, K. S. et al. They know the words, but not the music: Affective and semantic priming in individuals with psychopathy. Biol. Psychol. 73, 114–123. https://doi.org/10.1016/j.biopsycho.2005.12.006 (2006). · DOI
  37. Hare, R. M. Freedom and Reason (Clarendon Press, 1963).

Cited by

See all 46

Metadata

Authors
Aharoni, E., Fernandes, S., Brady, D. J., Alexander, C., Criner, M., Queen, K., Rando, J., Nahmias, E., & Crespo, V.
Venue
Scientific Reports
Publisher
Springer Science and Business Media LLC
Published
2024-04-30
Volume
14
Issue
1
ISSN
2045-2322
DOI
10.1038/s41598-024-58087-7
Cited by
46
References
15
Language
en
Licence

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Attributions toward artificial agents in a modified Moral Turing Test. https://app.cochat.ai/papers/10.1038/s41598-024-58087-7
The paper
Aharoni, E., Fernandes, S., Brady, D. J., Alexander, C., Criner, M., Queen, K., Rando, J., Nahmias, E., & Crespo, V. (2024). Attributions toward artificial agents in a modified Moral Turing Test. Scientific Reports. https://doi.org/10.1038/s41598-024-58087-7

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.