Score: 0

LLMs Meet Finance: Fine-Tuning Foundation Models for the Open FinLLM Leaderboard

Published: April 17, 2025 | arXiv ID: 2504.13125v1

By: Varun Rao , Youran Sun , Mahendra Kumar and more

Potential Business Impact:

Makes computers understand money and finance better.

Business Areas:
Funding Platform Financial Services, Lending and Investments

This paper investigates the application of large language models (LLMs) to financial tasks. We fine-tuned foundation models using the Open FinLLM Leaderboard as a benchmark. Building on Qwen2.5 and Deepseek-R1, we employed techniques including supervised fine-tuning (SFT), direct preference optimization (DPO), and reinforcement learning (RL) to enhance their financial capabilities. The fine-tuned models demonstrated substantial performance gains across a wide range of financial tasks. Moreover, we measured the data scaling law in the financial domain. Our work demonstrates the potential of large language models (LLMs) in financial applications.

Country of Origin
🇺🇸 United States

Page Count
4 pages

Category
Computer Science:
Computation and Language