Evaluating the Accuracy of Chatbots in Financial Literature

Orhan Erdem, Kristi Hassett, Feyzullah Egriboyun

arXiv 11 Nov 2024 · Artificial Intelligence

Abstract

We evaluate the reliability of two chatbots, ChatGPT (4o and o1-preview versions), and Gemini Advanced, in providing references on financial literature and employing novel methodologies. Alongside the conventional binary approach commonly used in the literature, we developed a nonbinary approach and a recency measure to assess how hallucination rates vary with how recent a topic is. After analyzing 150 citations, ChatGPT-4o had a hallucination rate of 20.0% (95% CI, 13.6%-26.4%), while the o1-preview had a hallucination rate of 21.3% (95% CI, 14.8%-27.9%). In contrast, Gemini Advanced exhibited higher hallucination rates: 76.7% (95% CI, 69.9%-83.4%). While hallucination rates increased for more recent topics, this trend was not statistically significant for Gemini Advanced. These findings emphasize the importance of verifying chatbot-provided references, particularly in rapidly evolving fields.

Citation extraction

No citation data for this paper: 2411.07031_source: not a tar archive and not gzip (Not a gzipped file (b'%P')). arXiv holds no LaTeX source for roughly 8% of econ.EM submissions (PDF-only), and those can never enter the citation graph.