IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2410.03724.html
   My bibliography  Save this paper

Large Language Models Overcome the Machine Penalty When Acting Fairly but Not When Acting Selfishly or Altruistically

Author

Listed:
  • Zhen Wang
  • Ruiqi Song
  • Chen Shen
  • Shiya Yin
  • Zhao Song
  • Balaraju Battu
  • Lei Shi
  • Danyang Jia
  • Talal Rahwan
  • Shuyue Hu

Abstract

In social dilemmas where the collective and self-interests are at odds, people typically cooperate less with machines than with fellow humans, a phenomenon termed the machine penalty. Overcoming this penalty is critical for successful human-machine collectives, yet current solutions often involve ethically-questionable tactics, like concealing machines' non-human nature. In this study, with 1,152 participants, we explore the possibility of closing this research question by using Large Language Models (LLMs), in scenarios where communication is possible between interacting parties. We design three types of LLMs: (i) Cooperative, aiming to assist its human associate; (ii) Selfish, focusing solely on maximizing its self-interest; and (iii) Fair, balancing its own and collective interest, while slightly prioritizing self-interest. Our findings reveal that, when interacting with humans, fair LLMs are able to induce cooperation levels comparable to those observed in human-human interactions, even when their non-human nature is fully disclosed. In contrast, selfish and cooperative LLMs fail to achieve this goal. Post-experiment analysis shows that all three types of LLMs succeed in forming mutual cooperation agreements with humans, yet only fair LLMs, which occasionally break their promises, are capable of instilling a perception among humans that cooperating with them is the social norm, and eliciting positive views on their trustworthiness, mindfulness, intelligence, and communication quality. Our findings suggest that for effective human-machine cooperation, bot manufacturers should avoid designing machines with mere rational decision-making or a sole focus on assisting humans. Instead, they should design machines capable of judiciously balancing their own interest and the interest of humans.

Suggested Citation

  • Zhen Wang & Ruiqi Song & Chen Shen & Shiya Yin & Zhao Song & Balaraju Battu & Lei Shi & Danyang Jia & Talal Rahwan & Shuyue Hu, 2024. "Large Language Models Overcome the Machine Penalty When Acting Fairly but Not When Acting Selfishly or Altruistically," Papers 2410.03724, arXiv.org, revised Oct 2024.
  • Handle: RePEc:arx:papers:2410.03724
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2410.03724
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Fernando P. Santos & Francisco C. Santos & Jorge M. Pacheco, 2018. "Social norm complexity and past reputations in the evolution of cooperation," Nature, Nature, vol. 555(7695), pages 242-245, March.
    2. Ernst Fehr & Ivo Schurtenberger, 2018. "Normative foundations of human cooperation," Nature Human Behaviour, Nature, vol. 2(7), pages 458-468, July.
    3. Murray Shanahan & Kyle McDonell & Laria Reynolds, 2023. "Role play with large language models," Nature, Nature, vol. 623(7987), pages 493-498, November.
    4. Andreoni, James A & Miller, John H, 1993. "Rational Cooperation in the Finitely Repeated Prisoner's Dilemma: Experimental Evidence," Economic Journal, Royal Economic Society, vol. 103(418), pages 570-585, May.
    5. Ernst Fehr & Simon Gächter, 2002. "Altruistic punishment in humans," Nature, Nature, vol. 415(6868), pages 137-140, January.
    6. Henrich, Joseph & Boyd, Robert & Bowles, Samuel & Camerer, Colin & Fehr, Ernst & Gintis, Herbert (ed.), 2004. "Foundations of Human Sociality: Economic Experiments and Ethnographic Evidence from Fifteen Small-Scale Societies," OUP Catalogue, Oxford University Press, number 9780199262052.
    7. repec:cup:judgdm:v:6:y:2011:i:8:p:771-781 is not listed on IDEAS
    8. Maggioni, Mario A. & Rossignoli, Domenico, 2023. "If it looks like a human and speaks like a human ... Communication and cooperation in strategic Human–Robot interactions," Journal of Behavioral and Experimental Economics (formerly The Journal of Socio-Economics), Elsevier, vol. 104(C).
    9. Ernst Fehr & Urs Fischbacher, 2003. "The nature of human altruism," Nature, Nature, vol. 425(6960), pages 785-791, October.
    10. Duffy, John & Feltovich, Nick, 2002. "Do Actions Speak Louder Than Words? An Experimental Comparison of Observation and Cheap Talk," Games and Economic Behavior, Elsevier, vol. 39(1), pages 1-27, April.
    11. Jean-François Bonnefon & Iyad Rahwan & Azim Shariff, 2024. "The Moral Psychology of Artificial Intelligence," Post-Print hal-04220044, HAL.
    Full references (including those not matched with items on IDEAS)

    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. Murnighan, J. Keith & Wang, Long, 2016. "The social world as an experimental game," Organizational Behavior and Human Decision Processes, Elsevier, vol. 136(C), pages 80-94.
    2. Kamei, Kenju, 2016. "Information Disclosure and Cooperation in a Finitely-repeated Dilemma: Experimental Evidence," MPRA Paper 75100, University Library of Munich, Germany.
    3. Gächter, Simon & Herrmann, Benedikt, 2011. "The limits of self-governance when cooperators get punished: Experimental evidence from urban and rural Russia," European Economic Review, Elsevier, vol. 55(2), pages 193-210, February.
    4. Tünde Paál & Tamás Bereczkei, 2015. "Punishment as a Means of Competition: Implications for Strong Reciprocity Theory," PLOS ONE, Public Library of Science, vol. 10(3), pages 1-14, March.
    5. Herbert Gintis, 2011. "The future of behavioral game theory," Mind & Society: Cognitive Studies in Economics and Social Sciences, Springer;Fondazione Rosselli, vol. 10(2), pages 97-102, December.
    6. Guererk, Oezguer & Rockenbach, Bettina & Wolff, Irenaeus, 2010. "The effects of punishment in dynamic public-good games," MPRA Paper 22097, University Library of Munich, Germany.
    7. Heller, William B. & Sieberg, Katri K., 2010. "Honor among thieves: Cooperation as a strategic response to functional unpleasantness," European Journal of Political Economy, Elsevier, vol. 26(3), pages 351-362, September.
    8. Freya Harrison & Claire El Mouden, 2011. "Exploring the Effects of Working for Endowments on Behaviour in Standard Economic Games," PLOS ONE, Public Library of Science, vol. 6(11), pages 1-6, November.
    9. Jang, Chaning & Lynham, John, 2015. "Where do social preferences come from?," Economics Letters, Elsevier, vol. 137(C), pages 25-28.
    10. D. Darcet & D. Sornette, 2008. "Quantitative determination of the level of cooperation in the presence of punishment in three public good experiments," Journal of Economic Interaction and Coordination, Springer;Society for Economic Science with Heterogeneous Interacting Agents, vol. 3(2), pages 137-163, December.
    11. Simon Gaechter & Benedikt Herrmann, 2008. "Reciprocity, culture, and human cooperation: Previous insights and a new cross-cultural experiment," Discussion Papers 2008-14, The Centre for Decision Research and Experimental Economics, School of Economics, University of Nottingham.
    12. Pan, Qiuhui & Wang, Linpeng & He, Mingfeng, 2020. "Social dilemma based on reputation and successive behavior," Applied Mathematics and Computation, Elsevier, vol. 384(C).
    13. Haruto Takagishi & Michiko Koizumi & Takayuki Fujii & Joanna Schug & Shinya Kameshima & Toshio Yamagishi, 2014. "The Role of Cognitive and Emotional Perspective Taking in Economic Decision Making in the Ultimatum Game," PLOS ONE, Public Library of Science, vol. 9(9), pages 1-7, September.
    14. Stoelhorst, J.W. & Richerson, Peter J., 2013. "A naturalistic theory of economic organization," Journal of Economic Behavior & Organization, Elsevier, vol. 90(S), pages 45-56.
    15. Simon Gaechter & Benedikt Herrmann, 2006. "The limits of self-governance in the presence of spite: Experimental evidence from urban and rural Russia," Discussion Papers 2006-13, The Centre for Decision Research and Experimental Economics, School of Economics, University of Nottingham.
    16. Fang, Ximeng & Freyer, Timo & Ho, Chui-Yee & Chen, Zihua & Goette, Lorenz, 2022. "Prosociality predicts individual behavior and collective outcomes in the COVID-19 pandemic," Social Science & Medicine, Elsevier, vol. 308(C).
    17. Quan, Ji & Yu, Junyu & Li, Xia & Wang, Xianjia, 2023. "Conditional switching between social excluders and loners promotes cooperation in spatial public goods game," Chaos, Solitons & Fractals, Elsevier, vol. 169(C).
    18. Maxwell N. Burton-Chellew & Victoire D’Amico & Claire Guérin, 2022. "The Strategy Method Risks Conflating Confusion with a Social Preference for Conditional Cooperation in Public Goods Games," Games, MDPI, vol. 13(6), pages 1-10, October.
    19. Gächter, Simon & Herrmann, Benedikt, 2011. "The limits of self-governance when cooperators get punished: Experimental evidence from urban and rural Russia," European Economic Review, Elsevier, vol. 55(2), pages 193-210, February.
    20. Yang, Luhe & Zhang, Lianzhong, 2021. "Environmental feedback in spatial public goods game," Chaos, Solitons & Fractals, Elsevier, vol. 142(C).

    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:2410.03724. 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.