IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2212.13371.html
   My bibliography  Save this paper

Measuring an artificial intelligence agent's trust in humans using machine incentives

Author

Listed:
  • Tim Johnson
  • Nick Obradovich

Abstract

Scientists and philosophers have debated whether humans can trust advanced artificial intelligence (AI) agents to respect humanity's best interests. Yet what about the reverse? Will advanced AI agents trust humans? Gauging an AI agent's trust in humans is challenging because--absent costs for dishonesty--such agents might respond falsely about their trust in humans. Here we present a method for incentivizing machine decisions without altering an AI agent's underlying algorithms or goal orientation. In two separate experiments, we then employ this method in hundreds of trust games between an AI agent (a Large Language Model (LLM) from OpenAI) and a human experimenter (author TJ). In our first experiment, we find that the AI agent decides to trust humans at higher rates when facing actual incentives than when making hypothetical decisions. Our second experiment replicates and extends these findings by automating game play and by homogenizing question wording. We again observe higher rates of trust when the AI agent faces real incentives. Across both experiments, the AI agent's trust decisions appear unrelated to the magnitude of stakes. Furthermore, to address the possibility that the AI agent's trust decisions reflect a preference for uncertainty, the experiments include two conditions that present the AI agent with a non-social decision task that provides the opportunity to choose a certain or uncertain option; in those conditions, the AI agent consistently chooses the certain option. Our experiments suggest that one of the most advanced AI language models to date alters its social behavior in response to incentives and displays behavior consistent with trust toward a human interlocutor when incentivized.

Suggested Citation

  • Tim Johnson & Nick Obradovich, 2022. "Measuring an artificial intelligence agent's trust in humans using machine incentives," Papers 2212.13371, arXiv.org.
  • Handle: RePEc:arx:papers:2212.13371
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2212.13371
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Simon Gächter & Elke Renner, 2010. "The effects of (incentivized) belief elicitation in public goods experiments," Experimental Economics, Springer;Economic Science Association, vol. 13(3), pages 364-377, September.
    2. repec:cup:judgdm:v:11:y:2016:i:5:p:527-536 is not listed on IDEAS
    3. Ernst Fehr, 2009. "On The Economics and Biology of Trust," Journal of the European Economic Association, MIT Press, vol. 7(2-3), pages 235-266, 04-05.
    4. March, Christoph, 2021. "Strategic interactions between humans and artificial intelligence: Lessons from experiments with computer players," Journal of Economic Psychology, Elsevier, vol. 87(C).
    5. F. Bailey Norwood & Jayson L. Lusk, 2011. "Social Desirability Bias in Real, Hypothetical, and Inferred Valuation Experiments," American Journal of Agricultural Economics, Agricultural and Applied Economics Association, vol. 93(2), pages 528-534.
    6. Charles Cannell & Ramon Henson, 1974. "Incentives, Motives, and Response Bias," NBER Chapters, in: Annals of Economic and Social Measurement, Volume 3, number 2, pages 307-317, National Bureau of Economic Research, Inc.
    7. Johnson, Noel D. & Mislin, Alexandra A., 2011. "Trust games: A meta-analysis," Journal of Economic Psychology, Elsevier, vol. 32(5), pages 865-889.
    8. Smith, Vernon L, 1976. "Experimental Economics: Induced Value Theory," American Economic Review, American Economic Association, vol. 66(2), pages 274-279, May.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Christoph Engel & Max R. P. Grossmann & Axel Ockenfels, 2023. "Integrating machine behavior into human subject experiments: A user-friendly toolkit and illustrations," Discussion Paper Series of the Max Planck Institute for Research on Collective Goods 2024_01, Max Planck Institute for Research on Collective Goods.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Francesco Bogliacino & Laura Jiménez & Gianluca Grimalda, 2015. "Consultative, Democracy and Trust," Documentos de Trabajo, Escuela de Economía 12696, Universidad Nacional de Colombia, FCE, CID.
    2. Bogliacino, Francesco & Codagnone, Cristiano, 2021. "Microfoundations, behaviour, and evolution: Evidence from experiments," Structural Change and Economic Dynamics, Elsevier, vol. 56(C), pages 372-385.
    3. Bogliacino, Francesco & Grimalda, Gianluca & Jimenez, Laura, 2017. "Consultative Democracy & Trust," MPRA Paper 82138, University Library of Munich, Germany.
    4. Bogliacino, Francesco & Jiménez Lozano, Laura & Grimalda, Gianluca, 2018. "Consultative democracy and trust11We thank Vanessa Carrillo, Jairo Paéz and Daniel Reyes for their help during the experiments. A special thanks to Franci Beltrán, Jairo Paéz and Alfonso Peña for prov," Structural Change and Economic Dynamics, Elsevier, vol. 44(C), pages 55-67.
    5. Daniel Woods & Maroš Servátka, 2019. "Nice to you, nicer to me: Does self-serving generosity diminish the reciprocal response?," Experimental Economics, Springer;Economic Science Association, vol. 22(2), pages 506-529, June.
    6. Goeschl, Timo & Jarke, Johannes, 2014. "Trust, but verify? When trustworthiness is observable only through (costly) monitoring," WiSo-HH Working Paper Series 20, University of Hamburg, Faculty of Business, Economics and Social Sciences, WISO Research Laboratory.
    7. Holden, Stein T. & Tilahun, Mesfin, 2019. "How Do Social Preferences and Norms of Reciprocity affect Generalized and Particularized Trust?," CLTS Working Papers 8/19, Norwegian University of Life Sciences, Centre for Land Tenure Studies, revised 10 Oct 2019.
    8. Cicognani, Simona & Romagnoli, Giorgia & Soraperra, Ivan, 2024. "Fostering trust: When the rhetoric of sharing can backfire," Journal of Economic Psychology, Elsevier, vol. 102(C).
    9. Zhang, Zhe & Zhang, Xu & Putterman, Louis, 2019. "Trust and cooperation at a confluence of worlds: An experiment in Xinjiang, China," Journal of Economic Behavior & Organization, Elsevier, vol. 161(C), pages 128-144.
    10. Stein T Holden & Mesfin Tilahun, 2021. "Preferences, trust, and performance in youth business groups," PLOS ONE, Public Library of Science, vol. 16(9), pages 1-28, September.
    11. Martin G. Kocher, 2015. "How Trust in Social Dilemmas Evolves with Age," CESifo Working Paper Series 5447, CESifo.
    12. Zubair, Maria & Khanum, Ayesha & Nasir, Marjan, 2018. "Transfer Of Behavioral Traits From Parents To Children: An Experimental Approach," MPRA Paper 92121, University Library of Munich, Germany.
    13. Fehr, Dietmar & Rau, Hannes & Trautmann, Stefan T. & Xu, Yilong, 2020. "Inequality, fairness and social capital," European Economic Review, Elsevier, vol. 129(C).
    14. Michal Bauer & Nathan Fiala & Ian Levely, 2018. "Trusting Former Rebels: An Experimental Approach to Understanding Reintegration after Civil War," Economic Journal, Royal Economic Society, vol. 128(613), pages 1786-1819, August.
    15. Kim, Jeongbin & Putterman, Louis & Zhang, Xinyi, 2022. "Trust, Beliefs and Cooperation: Excavating a Foundation of Strong Economies," European Economic Review, Elsevier, vol. 147(C).
    16. Francesco Bogliacino & Gianluca Grimalda & Laura Jiménez & Daniel Reyes Galvis & Cristiano Codagnone, 2022. "Trust and trustworthiness after a land restitution program: lab-in-the-field evidence from Colombia," Constitutional Political Economy, Springer, vol. 33(2), pages 135-161, June.
    17. Keser, Claudia & Markstädter, Andreas, 2014. "Informational asymmetries in laboratory asset markets with state-dependent fundamentals," University of Göttingen Working Papers in Economics 207, University of Goettingen, Department of Economics.
    18. Kovacs, Roxanne & Dunaiski, Maurice & Galizzi, Matteo M. & Grimalda, Gianluca & Hortala-Vallve, Rafael & Murtin, Fabrice & Putterman, Louis, 2024. "The determinants of trust: findings from large, representative samples in six OECD countries," LSE Research Online Documents on Economics 124608, London School of Economics and Political Science, LSE Library.
    19. Lönnqvist, Jan-Erik & Verkasalo, Markku & Walkowitz, Gari & Wichardt, Philipp C., 2015. "Measuring individual risk attitudes in the lab: Task or ask? An empirical comparison," Journal of Economic Behavior & Organization, Elsevier, vol. 119(C), pages 254-266.
    20. Quang Nguyen & Marie Claire Villeval & Hui Xu, 2012. "Trust and Trustworthiness under the Prospect Theory: A field experiment in Vietnam," Working Papers halshs-00730609, HAL.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:2212.13371. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.