THaLLE: Text Hyperlocally Augmented Large Language Extension -- Technical Report
This work addresses the need for more practical and cost-effective LLMs in financial analysis, though it is incremental as it builds on existing fine-tuning techniques.
The authors tackled the problem of large language models being computationally expensive and not fully proficient in financial analysis by fine-tuning a series of 8B LLMs, achieving the highest performance on mock CFA exams compared to models of similar size.
Recent advancements in Large Language Models (LLMs) have revealed new capabilities and opportunities across the technological landscape. However, the practicality of very large LLMs is challenged by their high compute cost, which does not justify the benefits given their limited capability compared to humans. While smaller, more practical LLMs have shown potential in financial analysis, though they are not yet fully proficient, as evidenced by their near-passing performance on the Chartered Financial Analyst (CFA) exam. In this work, we present Financial Analyst Extension to our Text Hyperlocally Augmented Large Language Extension (THaLLE), a series of 8B LLMs consistently achieving highest performance on mock CFA exams against models of comparable size. We thoroughly document the fine-tuning techniques used to facilitate future research. Additionally, we introduce the use of Flare CFA, a publicly available dataset for evaluating LLMs as a financial advisor.