IDEAS home Printed from https://ideas.repec.org/a/eee/beexfi/v43y2024ics2214635024000868.html
   My bibliography  Save this article

Human bias in AI models? Anchoring effects and mitigation strategies in large language models

Author

Listed:
  • Nguyen, Jeremy K.

Abstract

This study builds on the seminal work of Tversky and Kahneman (1974), exploring the presence and extent of anchoring bias in forecasts generated by four Large Language Models (LLMs): GPT-4, Claude 2, Gemini Pro and GPT-3.5. In contrast to recent findings of advanced reasoning capabilities in LLMs, our randomised controlled trials reveal the presence of anchoring bias across all models: forecasts are significantly influenced by prior mention of high or low values. We examine two mitigation prompting strategies, ‘Chain of Thought’ and ‘ignore previous’, finding limited and varying degrees of effectiveness. Our results extend the anchoring bias research in finance beyond human decision-making to encompass LLMs, highlighting the importance of deliberate and informed prompting in AI forecasting in both ad hoc LLM use and in crafting few-shot examples.

Suggested Citation

  • Nguyen, Jeremy K., 2024. "Human bias in AI models? Anchoring effects and mitigation strategies in large language models," Journal of Behavioral and Experimental Finance, Elsevier, vol. 43(C).
  • Handle: RePEc:eee:beexfi:v:43:y:2024:i:c:s2214635024000868
    DOI: 10.1016/j.jbef.2024.100971
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S2214635024000868
    Download Restriction: no

    File URL: https://libkey.io/10.1016/j.jbef.2024.100971?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Cen, Ling & Hilary, Gilles & Wei, K. C. John, 2013. "The Role of Anchoring Bias in the Equity Market: Evidence from Analysts’ Earnings Forecasts and Stock Returns," Journal of Financial and Quantitative Analysis, Cambridge University Press, vol. 48(1), pages 47-76, February.
    2. Yiting Chen & Tracy Xiao Liu & You Shan & Songfa Zhong, 2023. "The emergence of economic rationality of GPT," Proceedings of the National Academy of Sciences, Proceedings of the National Academy of Sciences, vol. 120(51), pages 2316205120-, December.
    3. Goodell, John W. & Kumar, Satish & Lim, Weng Marc & Pattnaik, Debidutta, 2021. "Artificial intelligence and machine learning in finance: Identifying foundations, themes, and research clusters from bibliometric analysis," Journal of Behavioral and Experimental Finance, Elsevier, vol. 32(C).
    4. Hendy, Patrick & Slonim, Robert & Atalay, Kadir, 2021. "Unsticking credit card repayments from the minimum: Advice, anchors and financial incentives," Journal of Behavioral and Experimental Finance, Elsevier, vol. 30(C).
    5. Shanmuganathan, Manchuna, 2020. "Behavioural finance in an era of artificial intelligence: Longitudinal case study of robo-advisors in investment decisions," Journal of Behavioral and Experimental Finance, Elsevier, vol. 27(C).
    6. Meub, Lukas & Proeger, Till, 2016. "Can anchoring explain biased forecasts? Experimental evidence," Journal of Behavioral and Experimental Finance, Elsevier, vol. 12(C), pages 1-13.
    7. Gurdgiev, Constantin & O’Loughlin, Daniel, 2020. "Herding and anchoring in cryptocurrency markets: Investor reaction to fear and uncertainty," Journal of Behavioral and Experimental Finance, Elsevier, vol. 25(C).
    8. Dowling, Michael & Lucey, Brian, 2023. "ChatGPT for (Finance) research: The Bananarama Conjecture," Finance Research Letters, Elsevier, vol. 53(C).
    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. Lukas Meub & Till Proeger, 2018. "Are groups ‘less behavioral’? The case of anchoring," Theory and Decision, Springer, vol. 85(2), pages 117-150, August.
    2. Chen, Chun & He, Fangyi & Lin, Lei, 2024. "Anchoring effect, prospect value and stock return," International Review of Economics & Finance, Elsevier, vol. 89(PA), pages 1539-1556.
    3. Kumar, Satish & Rao, Sandeep & Goyal, Kirti & Goyal, Nisha, 2022. "Journal of Behavioral and Experimental Finance: A bibliometric overview," Journal of Behavioral and Experimental Finance, Elsevier, vol. 34(C).
    4. Peng, Weike & Gao, Jiaxin & Chen, Yuntian & Wang, Shengwei, 2024. "Bridging data barriers among participants: Assessing the potential of geoenergy through federated learning," Applied Energy, Elsevier, vol. 367(C).
    5. Régis BRETON & Sébastien GALANTI & Christophe HURLIN & Anne-Gaël VAUBOURG, 2011. "Does the firm-analyst relationship matter in explaining analysts' earnings forecast errors?," LEO Working Papers / DR LEO 469, Orleans Economics Laboratory / Laboratoire d'Economie d'Orleans (LEO), University of Orleans.
    6. Siddiqi, Hammad, 2015. "Anchoring and Adjustment Heuristic: A Unified Explanation for Equity Puzzles," MPRA Paper 68729, University Library of Munich, Germany.
    7. Yuwei Yin & Yazheng Yang & Jian Yang & Qi Liu, 2023. "FinPT: Financial Risk Prediction with Profile Tuning on Pretrained Foundation Models," Papers 2308.00065, arXiv.org.
    8. Rice, Stephen & Crouse, Sean R. & Winter, Scott R. & Rice, Connor, 2024. "The advantages and limitations of using ChatGPT to enhance technological research," Technology in Society, Elsevier, vol. 76(C).
    9. Hao, Ying & Chou, Robin K. & Ko, Kuan-Cheng & Yang, Nien-Tzu, 2018. "The 52-week high, momentum, and investor sentiment," International Review of Financial Analysis, Elsevier, vol. 57(C), pages 167-183.
    10. Seiler, Volker & Fanenbruck, Katharina Maria, 2021. "Acceptance of digital investment solutions: The case of robo advisory in Germany," Research in International Business and Finance, Elsevier, vol. 58(C).
    11. Zeeshan Ahmed & Shahid Rasool & Qasim Saleem & Mubashir Ali Khan & Shamsa Kanwal, 2022. "Mediating Role of Risk Perception Between Behavioral Biases and Investor’s Investment Decisions," SAGE Open, , vol. 12(2), pages 21582440221, May.
    12. Anup Kumar & Santosh Kumar Shrivastav & Avinash K. Shrivastava & Rashmi Ranjan Panigrahi & Abbas Mardani & Fausto Cavallaro, 2023. "Sustainable Supply Chain Management, Performance Measurement, and Management: A Review," Sustainability, MDPI, vol. 15(6), pages 1-25, March.
    13. Horobet, Alexandra & Boubaker, Sabri & Belascu, Lucian & Negreanu, Cristina Carmencita & Dinca, Zeno, 2024. "Technology-driven advancements: Mapping the landscape of algorithmic trading literature," Technological Forecasting and Social Change, Elsevier, vol. 209(C).
    14. Liyun Zhou & Weinan Lin & Chunpeng Yang, 2024. "Investor trading behavior and asset prices: Evidence from quantile regression analysis," International Journal of Finance & Economics, John Wiley & Sons, Ltd., vol. 29(2), pages 1722-1744, April.
    15. Meub, Lukas & Proeger, Till E., 2015. "Anchoring in social context," Journal of Behavioral and Experimental Economics (formerly The Journal of Socio-Economics), Elsevier, vol. 55(C), pages 29-39.
    16. Chen, An-Sing & Nguyen, Huong Thi, 2024. "A new perspective on how investor sentiment affects herding behavior in the cryptocurrency market," Finance Research Letters, Elsevier, vol. 67(PA).
    17. Gang Kou & Yang Lu, 2025. "FinTech: a literature review of emerging financial technologies and applications," Financial Innovation, Springer;Southwestern University of Finance and Economics, vol. 11(1), pages 1-34, December.
    18. Afaq Khattak & Hamad Almujibah & Ahmed Elamary & Caroline Mongina Matara, 2022. "Interpretable Dynamic Ensemble Selection Approach for the Prediction of Road Traffic Injury Severity: A Case Study of Pakistan’s National Highway N-5," Sustainability, MDPI, vol. 14(19), pages 1-18, September.
    19. Naeem, Muhammad Abubakr & Karim, Sitara & Tiwari, Aviral Kumar, 2022. "Quantifying systemic risk in US industries using neural network quantile regression," Research in International Business and Finance, Elsevier, vol. 61(C).
    20. Kumar, Satish & Chavan, Meena & Pandey, Nitesh, 2023. "Journal of International Management: A 25-year review using bibliometric analysis," Journal of International Management, Elsevier, vol. 29(1).

    More about this item

    Keywords

    Anchoring bias; Artificial intelligence;

    JEL classification:

    • C45 - Mathematical and Quantitative Methods - - Econometric and Statistical Methods: Special Topics - - - Neural Networks and Related Topics
    • D81 - Microeconomics - - Information, Knowledge, and Uncertainty - - - Criteria for Decision-Making under Risk and Uncertainty

    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:eee:beexfi:v:43:y:2024:i:c:s2214635024000868. 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: Catherine Liu (email available below). General contact details of provider: https://www.journals.elsevier.com/journal-of-behavioral-and-experimental-finance .

    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.