Augmenting Fundamental Analysis with Large Language Models: A RAG-Based System for Generating Investor Briefs

利用大语言模型增强基本面分析：一种基于 RAG 的投资者简报生成系统

Abstract: In this study, we examine the opportunities brought by Large Language Models (LLMs) to various aspects of fundamental analysis of companies based on their reports as well as data and documents describing macroeconomic situation like GDP and inflation changes as well as documents filled to the U.S. Securities and Exchange Commission (SEC) which can be found in EDGAR.

摘要： 在本研究中，我们探讨了大语言模型（LLM）为公司基本面分析的各个方面所带来的机遇。这些分析基于公司报告、描述宏观经济状况（如 GDP 和通胀变化）的数据与文档，以及提交给美国证券交易委员会（SEC）并可在 EDGAR 系统中查阅的文件。

We were preprocessing those data and than sending via API to gpt-4o model in a Retrieval-Augmented Generation (RAG) like regime. We prepared as well a document describing an exemplar investor knowledge based on Kitchin cycles.

我们对这些数据进行了预处理，随后以检索增强生成（RAG）的模式通过 API 发送给 gpt-4o 模型。此外，我们还准备了一份基于基钦周期（Kitchin cycles）的投资者知识范例文件。

We were scanning data important for analysis of 9 companies for 4 weeks. Using LLM we were producing automatic briefs about them. They were sent to nine participants who are individual investors to evaluate usefulness of such approach to data analysis.

我们对 9 家公司进行了为期 4 周的分析数据扫描，并利用大语言模型自动生成了关于这些公司的简报。随后，我们将这些简报发送给 9 位个人投资者参与者，以评估这种数据分析方法的实用性。

---

Paper Details:

• Authors: Bartosz Ziółko, Kacper Dobrzeniewski
• Date: 10 Jul 2026
• Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Portfolio Management (q-fin.PM); Trading and Market Microstructure (q-fin.TR)
• DOI: 10.48550/arXiv.2607.09121

论文详情：

• 作者： Bartosz Ziółko, Kacper Dobrzeniewski
• 日期： 2026 年 7 月 10 日
• 学科分类： 计算与语言 (cs.CL)；人工智能 (cs.AI)；投资组合管理 (q-fin.PM)；交易与市场微观结构 (q-fin.TR)
• DOI： 10.48550/arXiv.2607.09121