LLMs Meet Finance: Fine-Tuning Foundation Models for the Open FinLLM Leaderboard
By: Varun Rao , Youran Sun , Mahendra Kumar and more
Potential Business Impact:
Makes computers understand money and finance better.
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.
Similar Papers
Fine-tuning of lightweight large language models for sentiment classification on heterogeneous financial textual data
Computation and Language
Small AI models understand money news well.
A Survey of Large Language Models for Financial Applications: Progress, Prospects and Challenges
General Finance
Helps money computers understand and predict markets.
When FinTech Meets Privacy: Securing Financial LLMs with Differential Private Fine-Tuning
Cryptography and Security
Keeps your money secrets safe on your phone.