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

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.

@article{rao2025_2504.13125,
  title={ LLMs Meet Finance: Fine-Tuning Foundation Models for the Open FinLLM Leaderboard },
  author={ Varun Rao and Youran Sun and Mahendra Kumar and Tejas Mutneja and Agastya Mukherjee and Haizhao Yang },
  journal={arXiv preprint arXiv:2504.13125},
  year={ 2025 }
}