IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2205.11561.html
   My bibliography  Save this paper

Agreement and Statistical Efficiency in Bayesian Perception Models

Author

Listed:
  • Yash Deshpande
  • Elchanan Mossel
  • Youngtak Sohn

Abstract

Bayesian models of group learning are studied in Economics since the 1970s. and more recently in computational linguistics. The models from Economics postulate that agents maximize utility in their communication and actions. The Economics models do not explain the ``probability matching" phenomena that are observed in many experimental studies. To address these observations, Bayesian models that do not formally fit into the economic utility maximization framework were introduced. In these models individuals sample from their posteriors in communication. In this work we study the asymptotic behavior of such models on connected networks with repeated communication. Perhaps surprisingly, despite the fact that individual agents are not utility maximizers in the classical sense, we establish that the individuals ultimately agree and furthermore show that the limiting posterior is Bayes optimal. We explore the interpretation of our results in terms of Large Language Models (LLMs). In the positive direction our results can be interpreted as stating that interaction between different LLMs can lead to optimal learning. However, we provide an example showing how misspecification may lead LLM agents to be overconfident in their estimates.

Suggested Citation

  • Yash Deshpande & Elchanan Mossel & Youngtak Sohn, 2022. "Agreement and Statistical Efficiency in Bayesian Perception Models," Papers 2205.11561, arXiv.org, revised Aug 2023.
  • Handle: RePEc:arx:papers:2205.11561
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2205.11561
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Geanakoplos, John D. & Polemarchakis, Heraklis M., 1982. "We can't disagree forever," Journal of Economic Theory, Elsevier, vol. 28(1), pages 192-200, October.
    2. Gale, Douglas & Kariv, Shachar, 2003. "Bayesian learning in social networks," Games and Economic Behavior, Elsevier, vol. 45(2), pages 329-346, November.
    3. Rosenberg, Dinah & Solan, Eilon & Vieille, Nicolas, 2009. "Informational externalities and emergence of consensus," Games and Economic Behavior, Elsevier, vol. 66(2), pages 979-994, July.
    4. Michael Ostrovsky, 2012. "Information Aggregation in Dynamic Markets With Strategic Traders," Econometrica, Econometric Society, vol. 80(6), pages 2595-2647, November.
    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. Mueller-Frank, Manuel, 2014. "Does one Bayesian make a difference?," Journal of Economic Theory, Elsevier, vol. 154(C), pages 423-452.
    2. Elchanan Mossel & Manuel Mueller‐Frank & Allan Sly & Omer Tamuz, 2020. "Social Learning Equilibria," Econometrica, Econometric Society, vol. 88(3), pages 1235-1267, May.
    3. Pooya Molavi & Ceyhun Eksin & Alejandro Ribeiro & Ali Jadbabaie, 2016. "Learning to Coordinate in Social Networks," Operations Research, INFORMS, vol. 64(3), pages 605-621, June.
    4. Ding, Huihui & Pivato, Marcus, 2021. "Deliberation and epistemic democracy," Journal of Economic Behavior & Organization, Elsevier, vol. 185(C), pages 138-167.
    5. Azomahou, T. & Opolot, D., 2014. "Beliefs dynamics in communication networks," MERIT Working Papers 2014-034, United Nations University - Maastricht Economic and Social Research Institute on Innovation and Technology (MERIT).
    6. Arieli, Itai & Babichenko, Yakov & Shlomov, Segev, 2021. "Virtually additive learning," Journal of Economic Theory, Elsevier, vol. 197(C).
    7. Buechel, Berno & Hellmann, Tim & Klößner, Stefan, 2015. "Opinion dynamics and wisdom under conformity," Journal of Economic Dynamics and Control, Elsevier, vol. 52(C), pages 240-257.
    8. Jadbabaie, Ali & Molavi, Pooya & Sandroni, Alvaro & Tahbaz-Salehi, Alireza, 2012. "Non-Bayesian social learning," Games and Economic Behavior, Elsevier, vol. 76(1), pages 210-225.
    9. Daron Acemoglu & Asuman Ozdaglar, 2011. "Opinion Dynamics and Learning in Social Networks," Dynamic Games and Applications, Springer, vol. 1(1), pages 3-49, March.
    10. Syngjoo Choi & Douglas Gale & Shachar Kariv, 2012. "Social learning in networks: a Quantal Response Equilibrium analysis of experimental data," Review of Economic Design, Springer;Society for Economic Design, vol. 16(2), pages 135-157, September.
    11. Berno Buechel & Stefan Klößner & Martin Lochmüller & Heiko Rauhut, 2020. "The strength of weak leaders: an experiment on social influence and social learning in teams," Experimental Economics, Springer;Economic Science Association, vol. 23(2), pages 259-293, June.
    12. Alex Centeno, 2022. "A Structural Model for Detecting Communities in Networks," Papers 2209.08380, arXiv.org, revised Oct 2022.
    13. Camargo, Braz, 2014. "Learning in society," Games and Economic Behavior, Elsevier, vol. 87(C), pages 381-396.
    14. George J. Mailath & Larry Samuelson, 2020. "Learning under Diverse World Views: Model-Based Inference," American Economic Review, American Economic Association, vol. 110(5), pages 1464-1501, May.
    15. Siddarth Srinivasan & Ezra Karger & Yiling Chen, 2023. "Self-Resolving Prediction Markets for Unverifiable Outcomes," Papers 2306.04305, arXiv.org.
    16. Wuggenig, Mirjam, 2014. "Learning faster or more precisely? Strategic experimentation in networks," Discussion Paper Series of SFB/TR 15 Governance and the Efficiency of Economic Systems 485, Free University of Berlin, Humboldt University of Berlin, University of Bonn, University of Mannheim, University of Munich.
    17. Jérôme Mathis & Marcello Puca & Simone M. Sepe, 2021. "Deliberative Institutions and Optimality," CSEF Working Papers 614, Centre for Studies in Economics and Finance (CSEF), University of Naples, Italy, revised 09 Jun 2021.
    18. Vieille, Nicolas & Rosenberg, Dinah & Solan, Eilon, 2006. "Informational externalities and convergence of behavior," HEC Research Papers Series 856, HEC Paris.
    19. Linardi, Sera, 2017. "Accounting for noise in the microfoundations of information aggregation," Games and Economic Behavior, Elsevier, vol. 101(C), pages 334-353.
    20. Elchanan Mossel & Allan Sly & Omer Tamuz, 2015. "Strategic Learning and the Topology of Social Networks," Econometrica, Econometric Society, vol. 83(5), pages 1755-1794, September.

    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:2205.11561. 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.