用金融数据微调大模型，显著提升其处理金融任务的能力。
LLMs Meet Finance: Fine-Tuning Foundation Models for the Open FinLLM Leaderboard
- 基于Qwen2.5和Deepseek-R1，采用SFT、DPO等方法微调
- 在多个金融任务上性能明显提升，验证了模型有效性
- 揭示金融领域数据量与模型表现的关系，适合金融AI研究者
本文研究大语言模型（LLMs）在金融任务中的应用。我们以Open FinLLM Leaderboard为基准，对Qwen2.5和Deepseek-R1等基础模型进行微调，采用监督微调（SFT）、直接偏好优化（DPO）和强化学习（RL）等技术，显著提升了模型的金融能力。实验表明，微调后的模型在多种金融任务中表现优异。此外，我们还测量了金融领域的数据缩放规律。本工作展示了大语言模型在金融应用中的巨大潜力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。