FinCoT：基於專家金融推理的思維鏈接基礎

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，一種結構化的思維鏈（CoT）提示方法，該方法融合了領域專家財務推理的見解，以指導大型語言模型的推理軌跡。我們探討了FinNLP中的三種主要提示風格：(1) 標準提示——零樣本提示；(2) 非結構化CoT——不帶有明確推理結構的CoT提示，例如使用標籤；(3) 結構化CoT提示——帶有定義結構化推理步驟的明確指令或示例的CoT提示。此前，FinNLP主要集中於使用標準或非結構化CoT提示進行提示工程。然而，結構化CoT提示在先前的研究中受到的關注有限。此外，結構化CoT提示中的推理結構設計通常基於非領域專家的啟發式方法。在本研究中，我們探討了FinNLP中的每種提示方法。我們評估了三種主要提示風格及FinCoT在涵蓋十個金融領域的CFA風格問題上的表現。我們觀察到，FinCoT將性能從63.2%提升至80.5%，Qwen-2.5-7B-Instruct從69.7%提升至74.2%，同時相比結構化CoT提示，生成的標記數量減少了八倍。我們的研究結果表明，與領域對齊的結構化提示不僅能提升性能並降低推理成本，還能產生更具可解釋性且與專家對齊的推理軌跡。

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.