FinCoT：将思维链根植于专家级金融推理

FinCoT: Grounding Chain-of-Thought in Expert Financial Reasoning

June 19, 2025

作者: Natapong Nitarach, Warit Sirichotedumrong, Panop Pitchayarthorn, Pittawat Taveekitworachai, Potsawee Manakul, Kunat Pipatanakul

cs.AI

摘要

本文提出了FinCoT，一种结构化的思维链（CoT）提示方法，该方法融入了领域专家金融推理的洞见，以指导大型语言模型的推理轨迹。我们研究发现，在金融自然语言处理（FinNLP）中存在三种主要的提示风格：（1）标准提示——零样本提示；（2）非结构化CoT——无明确推理结构的CoT提示，如使用标签；（3）结构化CoT提示——带有明确指令或示例的CoT提示，这些指令或示例定义了结构化的推理步骤。以往，FinNLP主要侧重于使用标准或非结构化CoT提示进行提示工程。然而，结构化CoT提示在先前工作中受到的关注有限。此外，结构化CoT提示中的推理结构设计往往基于非领域专家的启发式方法。在本研究中，我们探讨了FinNLP中的每种提示方法。我们评估了三种主要提示风格及FinCoT在涵盖十个金融领域的CFA式问题上的表现。我们观察到，FinCoT将性能从63.2%提升至80.5%，Qwen-2.5-7B-Instruct从69.7%提升至74.2%，同时相比结构化CoT提示减少了八倍的生成令牌数。我们的研究结果表明，与领域对齐的结构化提示不仅提升了性能、降低了推理成本，还生成了更具可解释性且与专家推理轨迹一致的结果。

English

This paper presents FinCoT, a structured chain-of-thought (CoT) prompting approach that incorporates insights from domain-specific expert financial reasoning to guide the reasoning traces of large language models. We investigate that there are three main prompting styles in FinNLP: (1) standard prompting--zero-shot prompting; (2) unstructured CoT--CoT prompting without an explicit reasoning structure, such as the use of tags; and (3) structured CoT prompting--CoT prompting with explicit instructions or examples that define structured reasoning steps. Previously, FinNLP has primarily focused on prompt engineering with either standard or unstructured CoT prompting. However, structured CoT prompting has received limited attention in prior work. Furthermore, the design of reasoning structures in structured CoT prompting is often based on heuristics from non-domain experts. In this study, we investigate each prompting approach in FinNLP. We evaluate the three main prompting styles and FinCoT on CFA-style questions spanning ten financial domains. We observe that FinCoT improves performance from 63.2% to 80.5% and Qwen-2.5-7B-Instruct from 69.7% to 74.2%, while reducing generated tokens eight-fold compared to structured CoT prompting. Our findings show that domain-aligned structured prompts not only improve performance and reduce inference costs but also yield more interpretable and expert-aligned reasoning traces.