用金融专家思维模板引导大模型，提升财务推理准确率。
FinCoT: Grounding Chain-of-Thought in Expert Financial Reasoning
- 引入金融领域专家设计的结构化思维链模板
- 模型准确率最高提升17.3个百分点，输出长度减少近9倍
- 适合缺乏金融训练的大模型使用，结果更可解释
本文提出FinCoT，一种将领域专家金融推理模板嵌入结构化思维链（CoT）提示框架的方法。在十类CFA风格金融任务中，对比了三种提示方式：标准提示、非结构化思维链和结构化思维链。现有研究多集中于前两种，而结构化思维链缺乏领域知识融合。FinCoT作为首个结合专家蓝本的金融专用提示方法，使通用模型Qwen3-8B-Base准确率从63.2%提升至80.5%，金融专用模型Fin-R1（7B）从65.7%提升至75.7%，同时分别减少8.9倍和1.16倍输出长度。实验表明，该方法对未经过金融微调的模型效果最显著，不仅能提升性能、降低推理成本，还能生成更可解释且符合专家逻辑的推理过程。
原文摘要 · Abstract (English)
This paper presents FinCoT, a structured chain-of-thought (CoT) prompting framework that embeds domain-specific expert financial reasoning blueprints to guide large language models' behaviors. We identify three main prompting styles in financial NLP (FinNLP): (1) standard prompting (zero-shot), (2) unstructured CoT (free-form reasoning), and (3) structured CoT (with explicitly structured reasoning steps). Prior work has mainly focused on the first two, while structured CoT remains underexplored and lacks domain expertise incorporation. Therefore, we evaluate all three prompting approaches across ten CFA-style financial domains and introduce FinCoT as the first structured finance-specific prompting approach incorporating blueprints from domain experts. FinCoT improves the accuracy of a general-purpose model, Qwen3-8B-Base, from 63.2% to 80.5%, and boosts Fin-R1 (7B), a finance-specific model, from 65.7% to 75.7%, while reducing output length by up to 8.9x and 1.16x compared to structured CoT methods, respectively. We find that FinCoT proves most effective for models lacking financial post-training. Our findings show that FinCoT does not only improve performance and reduce inference costs but also yields more interpretable and expert-aligned reasoning traces.
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。