用市场反馈强化LLM，生成更精准的交易信号
FinRLlama: A Solution to LLM-Engineered Signals Challenge at FinRL Contest 2024
- 设计基于市场反馈的提示框架，微调LLaMA-3.2-3B模型
- 在任务二中实现信号一致性与交易结果优化，获冠军
- 适合对金融时序建模与LLM融合感兴趣的开发者
针对ACM ICAIF 2024 FinRL挑战赛的任务二，本文提出一种新型提示框架，通过市场反馈强化学习（RLMF）微调大语言模型（LLM）。该框架融合市场特异性特征与短期价格动态，提升交易信号精度。传统LLM虽擅长情感分析，但缺乏金融场景的上下文对齐性。我们采用定制化的RLMF提示设计，对LLaMA-3.2-3B-Instruct模型进行微调，整合历史市场数据与基于奖励的反馈机制。评估结果显示，该框架在信号一致性和交易结果紧致性上优于基线方法，荣获任务二冠军。项目代码已开源于GitHub。
原文摘要 · Abstract (English)
In response to Task II of the FinRL Challenge at ACM ICAIF 2024, this study proposes a novel prompt framework for fine-tuning large language models (LLM) with Reinforcement Learning from Market Feedback (RLMF). Our framework incorporates market-specific features and short-term price dynamics to generate more precise trading signals. Traditional LLMs, while competent in sentiment analysis, lack contextual alignment for financial market applications. To bridge this gap, we fine-tune the LLaMA-3.2-3B-Instruct model using a custom RLMF prompt design that integrates historical market data and reward-based feedback. Our evaluation shows that this RLMF-tuned framework outperforms baseline methods in signal consistency and achieving tighter trading outcomes; awarded as winner of Task II. You can find the code for this project on GitHub.
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。