New research has claimed that large language models, specifically GPT-4 (which powers certain versions of ChatGPT and several Microsoft Copilot-branded generative AI products) can analyze financial statements with greater accuracy than humans.
The findings from researchers at the University of Chicago suggest significant implications for the future of financial analysis and decision-making as AI becomes more common.
The study also highlights the versatility of generic, multi-functional LLMs such as GPT-4, which can provide similar capabilities to more specialized tools, noting: “We find that the prediction accuracy of the LLM is comparable to the performance of a narrowly trained state. modern ML model.”
LLMs are excellent at analyzing financial reports
In their tests, the researchers found that GPT-4 outperforms human analysts even without textual context, highlighting the technology’s 60% accuracy, compared to human analysts’ 53-57% range.
However, success did not come without some preliminary groundwork, with the article detailing the researchers’ use of thought chain prompts to formulate more appropriate and accurate responses.
Furthermore, the study found that GPT-4 and human analysts complement each other well – while the LLM excels in areas where humans may be inefficient or biased, humans add value where additional context is required.
GPT-4’s capabilities were attributed to its vast knowledge base and theoretical understanding, which allowed it to draw conclusions from data patterns even without specific financial training. Although the model turned out to have some limitations, the latest GPT-4o has already made progress. model significantly improves efficiency and turns into a multimodal model.
While there is some skepticism about generative AI’s readiness to replace human workers, its position as an integral support is becoming increasingly clear as human workers prepare to hybridize with the efficiency-enhancing technology.