FinCoT：在专家金融推理中 grounding 思维链
FinCoT: Grounding Chain-of-Thought in Expert Financial Reasoning
AI总结：
FinCoT通过整合专家金融推理蓝图，提升金融领域模型性能并减少推理成本，实现更可解释的推理过程。
摘要：
本文提出了FinCoT，一种结构化的思维链（CoT）提示框架，该框架嵌入了领域特定的专家金融推理蓝图，以指导大型语言模型的行为。我们识别出金融自然语言处理（FinNLP）中的三种主要提示风格：（1）标准提示（零样本），（2）无结构的CoT（自由形式推理），（3）结构化的CoT（具有显式结构化的推理步骤）。先前的工作主要集中在前两种，而结构化的CoT仍处于探索阶段，缺乏领域专业知识的整合。因此，我们评估了三种提示方法在十个CFA风格的金融领域中的表现，并引入FinCoT作为首个整合领域专家蓝图的结构化金融特定提示方法。FinCoT将通用模型Qwen3-8B-Base的准确率从63.2%提升到80.5%，并将专门用于金融的模型Fin-R1（7B）的准确率从65.7%提升到75.7%。同时，与结构化CoT方法相比，FinCoT将输出长度分别减少了高达8.9倍和1.16倍。我们发现，FinCoT对缺乏金融后训练的模型效果最为显著。我们的发现表明，FinCoT不仅提高了性能和降低了推理成本，还产生了更具解释性和专家对齐的推理轨迹。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
