arXiv cs.AI· Huan Phong Thai, Thu Anh Ngoc Le, Nhu Huynh Thi Le, Nhan Huu Tran, Lenh Cong Phan Pham, Hong Nhung Nguyen·· 4 小时前AI 评分18
用 RAG 增强股票市场信息检索
Enhancing Stock Market Information Retrieval with Retrieval-Augmented Generation
AI 导读
一项研究构建了面向股票市场信息的 RAG 系统,将检索与生成结合以提升金融文本生成的准确性和相关性。在 100 条股票市场相关查询的数据集上,系统取得较高 ROUGE-1、ROUGE-2 和 ROUGE-L 分数,平均响应时间为 1.16 秒。
正文 · 原文
Abstract:Natural Language Processing (NLP) has been widely applied in financial domains, enabling automated analysis and retrieval of stock market information. However, traditional NLP-based systems often struggle with maintaining contextual accuracy and generating relevant responses in dynamic financial environments. To address these challenges, Retrieval-Augmented Generation (RAG) models have emerged as a powerful solution, combining retrieval-based methods with generative capabilities to enhance response quality. In this study, we present a Retrieval-Augmented Generation (RAG) system designed to generate responses related to stock market information. The system integrates retrieval-based and generative approaches to enhance the accuracy and relevance of financial text generation. To evaluate its effectiveness, we employ the ROUGE metric, specifically ROUGE-1, ROUGE-2, and ROUGE-L, to measure lexical and structural similarity between generated and reference texts. Experimental results on a dataset of 100 stock market-related queries demonstrate high ROUGE scores, indicating strong alignment with reference documents. Additionally, we assess latency to evaluate the system responsiveness, achieving an average response time of 1.16 seconds. These findings confirm that our RAG model is capable of providing accurate and timely stock market insights, making it a promising approach for financial information retrieval.
| Comments: | The manuscript is 21 pages long and includes 4 figures and 3 tables. It was submitted to "Expert Systems with Applications" Journal on October 30, 2025, and was rejected without external peer review |
| Subjects: | Information Retrieval (cs.IR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.03747 [cs.IR] |
| (or arXiv:2611.03747v2 [cs.IR] for this version) | |
| https://doi.org/10.48550/arXiv.2611.03747 arXiv-issued DOI via DataCite |
Submission history
From: Nhung Nguyen Hong [view email]
[v1]
Mon, 2 Nov 2026 05:49:37 UTC (385 KB)
[v2]
Tue, 17 Nov 2026 05:16:29 UTC (385 KB)
来源:arXiv cs.AI · arxiv.org