IDEAS home Printed from https://ideas.repec.org/a/eee/finlet/v70y2024ics1544612324013783.html
   My bibliography  Save this article

ChatGPT: A canary in the coal mine or a parrot in the echo chamber? Detecting fraud with LLM: The case of FTX

Author

Listed:
  • Gregory, Gadzinski
  • Vito, Liuzzi

Abstract

Does the paradigm shift brought by Large Language Models (LLMs) hold the promise of revolutionizing financial analysis? Our article tackles this question by exploring fraud detection in cryptocurrency exchanges, with a focus on FTX. We study the abilities of generative artificial intelligence tools like ChatGPT to serve as early-warning systems of fraud and identify red flags in the particular and difficult case where no financial information is available. We recognize several challenges to provide insights beyond human knowledge. To achieve a higher degree of scrutiny, we highlight the role of sequential interactions between the AI Chatbot and the researcher as well as the inclusion of external contents, a technique known as Retrieval Augmented Generation (RAG). Therefore, this article serves as a cautionary tale on the necessary conditions to achieve augmented intelligence.

Suggested Citation

  • Gregory, Gadzinski & Vito, Liuzzi, 2024. "ChatGPT: A canary in the coal mine or a parrot in the echo chamber? Detecting fraud with LLM: The case of FTX," Finance Research Letters, Elsevier, vol. 70(C).
    • Handle: RePEc:eee:finlet:v:70:y:2024:i:c:s1544612324013783
    DOI: 10.1016/j.frl.2024.106349
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S1544612324013783
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.frl.2024.106349?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
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Chakraborty, Chiranjit & Joseph, Andreas, 2017. "Machine learning at central banks," Bank of England working papers 674, Bank of England.
    2. Christian Fieberg & Lars Hornuf & David J. Streich, 2023. "Using GPT-4 for Financial Advice," CESifo Working Paper Series 10529, CESifo.
    3. Dowling, Michael & Lucey, Brian, 2023. "ChatGPT for (Finance) research: The Bananarama Conjecture," Finance Research Letters, Elsevier, vol. 53(C).
    4. Cao, Sean & Jiang, Wei & Wang, Junbo & Yang, Baozhong, 2024. "From Man vs. Machine to Man + Machine: The art and AI of stock analyses," Journal of Financial Economics, Elsevier, vol. 160(C).
    5. David Vidal-Tom'as & Antonio Briola & Tomaso Aste, 2023. "FTX's downfall and Binance's consolidation: The fragility of centralised digital finance," Papers 2302.11371, arXiv.org, revised Dec 2023.
    6. Riccardo Blasis & Luca Galati & Alexander Webb & Robert I. Webb, 2023. "Intelligent design: stablecoins (in)stability and collateral during market turbulence," Financial Innovation, Springer;Southwestern University of Finance and Economics, vol. 9(1), pages 1-23, December.
    7. Tim Loughran & Bill Mcdonald, 2016. "Textual Analysis in Accounting and Finance: A Survey," Journal of Accounting Research, Wiley Blackwell, vol. 54(4), pages 1187-1230, September.
    8. Lee, Seungju & Lee, Jaewook & Lee, Yunyoung, 2023. "Dissecting the Terra-LUNA crash: Evidence from the spillover effect and information flow," Finance Research Letters, Elsevier, vol. 53(C).
    9. Ko, Hyungjin & Lee, Jaewook, 2024. "Can ChatGPT improve investment decisions? From a portfolio management perspective," Finance Research Letters, Elsevier, vol. 64(C).
    10. Briola, Antonio & Vidal-Tomás, David & Wang, Yuanrong & Aste, Tomaso, 2023. "Anatomy of a Stablecoin’s failure: The Terra-Luna case," Finance Research Letters, Elsevier, vol. 51(C).
    11. Leippold, Markus, 2023. "Thus spoke GPT-3: Interviewing a large-language model on climate finance," Finance Research Letters, Elsevier, vol. 53(C).
    12. Vidal-Tomás, David & Briola, Antonio & Aste, Tomaso, 2023. "FTX's downfall and Binance's consolidation: the fragility of centralised digital finance," LSE Research Online Documents on Economics 119902, London School of Economics and Political Science, LSE Library.
    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. Gregory, Gadzinski & Alessio, Castello & Vito, Liuzzi & Patrice, Sargenti, 2024. "Break a peg! A study of stablecoin co-instability," International Review of Financial Analysis, Elsevier, vol. 96(PA).
    2. Saengchote, Kanis & Samphantharak, Krislert, 2024. "Digital money creation and algorithmic stablecoin run," Finance Research Letters, Elsevier, vol. 64(C).
    3. Riccardo De Blasis & Luca Galati & Rosanna Grassi & Giorgio Rizzini, 2024. "Information Flow in the FTX Bankruptcy: A Network Approach," Papers 2407.12683, arXiv.org.
    4. Smales, Lee A., 2023. "Classification of RBA monetary policy announcements using ChatGPT," Finance Research Letters, Elsevier, vol. 58(PC).
    5. Kotiloglu, Serhan & Ometto, M. Paola, 2024. "An exploratory look at the role of ownership in initial coin offerings (ICO): Different audiences and ICO success," Journal of Business Venturing Insights, Elsevier, vol. 21(C).
    6. Marcin Wk{a}torek & Marcin Kr'olczyk & Jaros{l}aw Kwapie'n & Tomasz Stanisz & Stanis{l}aw Dro.zd.z, 2024. "Approaching multifractal complexity in decentralized cryptocurrency trading," Papers 2411.05951, arXiv.org.
    7. Jeong, Woojin & Park, Seongwan & Lee, Seungyun & Son, Bumho & Lee, Jaewook & Ko, Hyungjin, 2024. "Influence and predictive power of sentiment: Evidence from the lithium market," Finance Research Letters, Elsevier, vol. 68(C).
    8. Minh Tam Tammy Schlosky & Serkan Karadas & Sterling Raskie, 2024. "ChatGPT, Help! I Am in Financial Trouble," JRFM, MDPI, vol. 17(6), pages 1-39, June.
    9. Amadxarif, Zahid & Brookes, James & Garbarino, Nicola & Patel, Rajan & Walczak, Eryk, 2019. "The language of rules: textual complexity in banking reforms," Bank of England working papers 834, Bank of England.
    10. Michael Cary, 2024. "Herding and investor sentiment after the cryptocurrency crash: evidence from Twitter and natural language processing," Financial Innovation, Springer;Southwestern University of Finance and Economics, vol. 10(1), pages 1-23, December.
    11. Pelster, Matthias & Val, Joel, 2024. "Can ChatGPT assist in picking stocks?," Finance Research Letters, Elsevier, vol. 59(C).
    12. Cascavilla, Alessandro, 2024. "Between money and speculative asset: The role of financial literacy on the perception towards Bitcoin in Italy," Journal of Economic Psychology, Elsevier, vol. 102(C).
    13. Dionysopoulos, Lambis & Urquhart, Andrew, 2024. "10 years of stablecoins: Their impact, what we know, and future research directions," Economics Letters, Elsevier, vol. 244(C).
    14. repec:zbw:bofitp:2019_008 is not listed on IDEAS
    15. Jiao Ji & Oleksandr Talavera & Shuxing Yin, 2018. "The Hidden Information Content: Evidence from the Tone of Independent Director Reports," Working Papers 2018-28, Swansea University, School of Management.
    16. Umar, Tarik, 2022. "Complexity aversion when SeekingAlpha," Journal of Accounting and Economics, Elsevier, vol. 73(2).
    17. Drago, Carlo & Ginesti, Gianluca & Pongelli, Claudia & Sciascia, Salvatore, 2018. "Reporting strategies: What makes family firms beat around the bush? Family-related antecedents of annual report readability," Journal of Family Business Strategy, Elsevier, vol. 9(2), pages 142-150.
    18. Everett, Jeff & Shiraz Rahaman, Abu & Neu, Dean & Saxton, Gregory, 2024. "Letters to the editor, institutional experimentation, and the public accounting professional," CRITICAL PERSPECTIVES ON ACCOUNTING, Elsevier, vol. 99(C).
    19. Rybinski, Krzysztof, 2020. "The forecasting power of the multi-language narrative of sell-side research: A machine learning evaluation," Finance Research Letters, Elsevier, vol. 34(C).
    20. Rolf Uwe Fülbier & Thorsten Sellhorn, 2023. "Understanding and improving the language of business: How accounting and corporate reporting research can better serve business and society," Journal of Business Economics, Springer, vol. 93(6), pages 1089-1124, August.
    21. Chris Florackis & Christodoulos Louca & Roni Michaely & Michael Weber, 2023. "Cybersecurity Risk," The Review of Financial Studies, Society for Financial Studies, vol. 36(1), pages 351-407.

    More about this item

    Keywords

    LLMs; FTX; Fraud detection; RAG;
    All these keywords.

    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:finlet:v:70:y:2024:i:c:s1544612324013783. 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: http://www.elsevier.com/locate/frl .

    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.