IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2502.14708.html
   My bibliography  Save this paper

Human Misperception of Generative-AI Alignment: A Laboratory Experiment

Author

Listed:
  • Kevin He
  • Ran Shorrer
  • Mengjia Xia

Abstract

We conduct an incentivized laboratory experiment to study people's perception of generative artificial intelligence (GenAI) alignment in the context of economic decision-making. Using a panel of economic problems spanning the domains of risk, time preference, social preference, and strategic interactions, we ask human subjects to make choices for themselves and to predict the choices made by GenAI on behalf of a human user. We find that people overestimate the degree of alignment between GenAI's choices and human choices. In every problem, human subjects' average prediction about GenAI's choice is substantially closer to the average human-subject choice than it is to the GenAI choice. At the individual level, different subjects' predictions about GenAI's choice in a given problem are highly correlated with their own choices in the same problem. We explore the implications of people overestimating GenAI alignment in a simple theoretical model.

Suggested Citation

  • Kevin He & Ran Shorrer & Mengjia Xia, 2025. "Human Misperception of Generative-AI Alignment: A Laboratory Experiment," Papers 2502.14708, arXiv.org.
    • Handle: RePEc:arx:papers:2502.14708
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2502.14708
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. George Loewenstein & Ted O'Donoghue & Matthew Rabin, 2003. "Projection Bias in Predicting Future Utility," The Quarterly Journal of Economics, President and Fellows of Harvard College, vol. 118(4), pages 1209-1248.
    2. Benjamin Enke, 2020. "What You See Is All There Is," The Quarterly Journal of Economics, President and Fellows of Harvard College, vol. 135(3), pages 1363-1398.
    3. Benjamin Enke & Florian Zimmermann, 2019. "Correlation Neglect in Belief Formation," The Review of Economic Studies, Review of Economic Studies Ltd, vol. 86(1), pages 313-332.
    4. Uri Gneezy & Jan Potters, 1997. "An Experiment on Risk Taking and Evaluation Periods," The Quarterly Journal of Economics, President and Fellows of Harvard College, vol. 112(2), pages 631-645.
    5. Ashesh Rambachan & Jon Kleinberg & Sendhil Mullainathan & Jens Ludwig, 2020. "An Economic Approach to Regulating Algorithms," NBER Working Papers 27111, National Bureau of Economic Research, Inc.
    6. Nicole Immorlica & Brendan Lucier & Aleksandrs Slivkins, 2024. "Generative AI as Economic Agents," Papers 2406.00477, arXiv.org.
    7. Ko, Hyungjin & Lee, Jaewook, 2024. "Can ChatGPT improve investment decisions? From a portfolio management perspective," Finance Research Letters, Elsevier, vol. 64(C).
    8. Pedro Bordalo & Nicola Gennaioli & Andrei Shleifer, 2012. "Salience Theory of Choice Under Risk," The Quarterly Journal of Economics, President and Fellows of Harvard College, vol. 127(3), pages 1243-1285.
    9. Tristan Gagnon-Bartsch & Antonio Rosato, 2024. "Quality Is in the Eye of the Beholder: Taste Projection in Markets with Observational Learning," American Economic Review, American Economic Association, vol. 114(11), pages 3746-3787, November.
    10. John J. Horton, 2023. "Large Language Models as Simulated Economic Agents: What Can We Learn from Homo Silicus?," NBER Working Papers 31122, National Bureau of Economic Research, Inc.
    11. Chad Kendall & Ryan Oprea, 2024. "On the complexity of forming mental models," Quantitative Economics, Econometric Society, vol. 15(1), pages 175-211, January.
    12. John J. Horton, 2023. "Large Language Models as Simulated Economic Agents: What Can We Learn from Homo Silicus?," Papers 2301.07543, arXiv.org.
    13. Jon Kleinberg & Himabindu Lakkaraju & Jure Leskovec & Jens Ludwig & Sendhil Mullainathan, 2018. "Human Decisions and Machine Predictions," The Quarterly Journal of Economics, President and Fellows of Harvard College, vol. 133(1), pages 237-293.
    14. Rema Hanna & Sendhil Mullainathan & Joshua Schwartzstein, 2014. "Learning Through Noticing: Theory and Evidence from a Field Experiment," The Quarterly Journal of Economics, President and Fellows of Harvard College, vol. 129(3), pages 1311-1353.
    15. Sendhil Mullainathan & Joshua Schwartzstein & Andrei Shleifer, 2008. "Coarse Thinking and Persuasion," The Quarterly Journal of Economics, President and Fellows of Harvard College, vol. 123(2), pages 577-619.
    16. Kaufmann, Marc, 2022. "Projection bias in effort choices," Games and Economic Behavior, Elsevier, vol. 135(C), pages 368-393.
    17. Ignacio Esponda & Emanuel Vespa & Sevgi Yuksel, 2024. "Mental Models and Learning: The Case of Base-Rate Neglect," American Economic Review, American Economic Association, vol. 114(3), pages 752-782, March.
    18. Madarász, Kristóf & Danz, David & Wang, Stephanie, 2018. "The Biases of Others: Projection Equilibrium in an Agency Setting," CEPR Discussion Papers 12867, C.E.P.R. Discussion Papers.
    19. Matteo Tranchero & Cecil-Francis Brenninkmeijer & Arul Murugan & Abhishek Nagaraj, 2024. "Theorizing with Large Language Models," NBER Working Papers 33033, National Bureau of Economic Research, Inc.
    20. Erik Snowberg & Leeat Yariv, 2021. "Testing the Waters: Behavior across Participant Pools," American Economic Review, American Economic Association, vol. 111(2), pages 687-719, February.
    21. Pelster, Matthias & Val, Joel, 2024. "Can ChatGPT assist in picking stocks?," Finance Research Letters, Elsevier, vol. 59(C).
    22. Andrew Caplin, 2016. "Measuring and Modeling Attention," Annual Review of Economics, Annual Reviews, vol. 8(1), pages 379-403, October.
    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. Xavier Gabaix, 2017. "Behavioral Inattention," NBER Working Papers 24096, National Bureau of Economic Research, Inc.
    2. George Loewenstein & Zachary Wojtowicz, 2023. "The Economics of Attention," CESifo Working Paper Series 10712, CESifo.
    3. Ignacio Esponda & Emanuel Vespa, 2024. "Contingent Thinking and the Sure-Thing Principle: Revisiting Classic Anomalies in the Laboratory," The Review of Economic Studies, Review of Economic Studies Ltd, vol. 91(5), pages 2806-2831.
    4. Benjamin Handel & Joshua Schwartzstein, 2018. "Frictions or Mental Gaps: What's Behind the Information We (Don't) Use and When Do We Care?," Journal of Economic Perspectives, American Economic Association, vol. 32(1), pages 155-178, Winter.
    5. Niederle, Muriel & Vespa, Emanuel, 2023. "Cognitive Limitations: Failures of Contingent Thinking," University of California at San Diego, Economics Working Paper Series qt5q14p1np, Department of Economics, UC San Diego.
    6. Jingru Jia & Zehua Yuan & Junhao Pan & Paul E. McNamara & Deming Chen, 2024. "Decision-Making Behavior Evaluation Framework for LLMs under Uncertain Context," Papers 2406.05972, arXiv.org, revised Oct 2024.
    7. Ignacio Esponda & Emanuel Vespa & Sevgi Yuksel, 2024. "Mental Models and Learning: The Case of Base-Rate Neglect," American Economic Review, American Economic Association, vol. 114(3), pages 752-782, March.
    8. Shumiao Ouyang & Hayong Yun & Xingjian Zheng, 2024. "How Ethical Should AI Be? How AI Alignment Shapes the Risk Preferences of LLMs," Papers 2406.01168, arXiv.org, revised Aug 2024.
    9. Yuqi Nie & Yaxuan Kong & Xiaowen Dong & John M. Mulvey & H. Vincent Poor & Qingsong Wen & Stefan Zohren, 2024. "A Survey of Large Language Models for Financial Applications: Progress, Prospects and Challenges," Papers 2406.11903, arXiv.org.
    10. repec:oup:qjecon:v:128:y:2012:i:1:p:53-104 is not listed on IDEAS
    11. Pedro Bordalo & John Conlon & Nicola Gennaioli & Spencer Kwon & Andrei Shleifer, 2023. "How People Use Statistics," Working Papers 699, IGIER (Innocenzo Gasparini Institute for Economic Research), Bocconi University.
    12. Gary Charness & Brian Jabarian & John List, 2023. "Generation Next: Experimentation with AI," Artefactual Field Experiments 00777, The Field Experiments Website.
    13. Chad Kendall & Ryan Oprea, 2024. "On the complexity of forming mental models," Quantitative Economics, Econometric Society, vol. 15(1), pages 175-211, January.
    14. Michel, Christian, 2017. "Market regulation of voluntary add-on contracts," International Journal of Industrial Organization, Elsevier, vol. 54(C), pages 239-268.
    15. Niculaescu, Corina E. & Sangiorgi, Ivan & Bell, Adrian R., 2023. "Does personal experience with COVID-19 impact investment decisions? Evidence from a survey of US retail investors," International Review of Financial Analysis, Elsevier, vol. 88(C).
    16. Evan Piermont, 2021. "Hypothetical Expected Utility," Papers 2106.15979, arXiv.org, revised Jul 2021.
    17. Philippe Jehiel, 2022. "Analogy-Based Expectation Equilibrium and Related Concepts:Theory, Applications, and Beyond," Working Papers halshs-03735680, HAL.
    18. Banerjee, Ritwik & Gupta, Nabanita Datta & Villeval, Marie Claire, 2020. "Feedback spillovers across tasks, self-confidence and competitiveness," Games and Economic Behavior, Elsevier, vol. 123(C), pages 127-170.
    19. Chen Lian & Yueran Ma & Carmen Wang, 2019. "Low Interest Rates and Risk-Taking: Evidence from Individual Investment Decisions," The Review of Financial Studies, Society for Financial Studies, vol. 32(6), pages 2107-2148.
    20. Kevin Leyton-Brown & Paul Milgrom & Neil Newman & Ilya Segal, 2024. "Artificial Intelligence and Market Design: Lessons Learned from Radio Spectrum Reallocation," NBER Chapters, in: New Directions in Market Design, National Bureau of Economic Research, Inc.
    21. Castagnetti, Alessandro & Schmacker, Renke, 2022. "Protecting the ego: Motivated information selection and updating," European Economic Review, 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:2502.14708. 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.