用大模型自动总结金融新闻，提升投资决策效率。
Automated Summarization of Financial News Using Large Language Models and Retrieval-Augmented Generation: An Early Empirical Study (Fall 2023)
- 构建新闻、公司背景与股价数据融合的自动化摘要流水线
- Falcon-7B结合链式摘要在10家公司上准确覆盖所有事件
- 揭示RAG在小模型中易产生幻觉和重复，具现实警示意义
股票分析师和投资者每日面临信息过载：海量公司新闻难以手动处理，但遗漏关键信息会直接影响投资判断。本项目于2023年秋季在乔治华盛顿大学开展，探索大语言模型是否能可靠实现该任务自动化。我们构建了从News API获取新闻、Wikipedia获取公司背景、Yahoo Finance获取股价数据的流水线，覆盖苹果、微软等十家上市公司。由于大模型无法直接处理表格数据，我们设计了将股价数据转化为自然语言描述的模板。测试了两种摘要方法（链式摘要与基于FAISS的检索增强生成）及三种开源模型（Falcon-7B-Instruct、DistilBART-CNN-12-6、BART-Large-XSum），并使用GPT（text-davinci-003）生成股价摘要。Falcon-7B搭配链式摘要表现最佳，完整且连贯地覆盖所有新闻事件。而RAG虽理论上可行，但在高检索参数k下导致Falcon严重重复，BART-Large出现事实幻觉。两类大模型方法均优于基础的前3句摘要基准（ROUGE-1）。研究还开发了交互式股票可视化仪表板。该项目在RAG金融工具普及前完成，所记录的失败模式——尤其小模型中RAG引发的幻觉——至今仍具参考价值。
原文摘要 · Abstract (English)
Stock market analysts and investors face a daily challenge: too much financial news, too little time. Manually reading and synthesizing hundreds of company-specific articles is impractical, yet missing key information can directly affect investment decisions. This project, conducted at George Washington University in Fall 2023, explores whether Large Language Models can automate this process reliably. We built a pipeline that pulls news articles from the News API, company background from Wikipedia, and stock price data from Yahoo Finance for ten major companies (AAPL, MSFT, GOOGL, AMZN, META, TSLA, JPM, NVDA, WMT, DIS). Because LLMs cannot directly process numerical tables, we developed a simple but effective template that converts stock data into natural language narratives. We then tested two summarization approaches (Summarize Chains and Retrieval-Augmented Generation with FAISS) across three open-source models (Falcon-7B-Instruct, DistilBART-CNN-12-6, BART-Large-XSum) for news, and GPT (text-davinci-003) for stock summaries. Falcon-7B with Summarize Chains gave the best results, covering all news events accurately and coherently. RAG, while promising in theory, caused severe repetition in Falcon and hallucinated facts in BART-Large when k was large. Both LLM-based approaches outperformed a simple Lead-3 baseline on ROUGE-1. We also built a Streamlit dashboard for interactive stock visualization. The work was done in Fall 2023, before RAG-based financial tools became widespread, and the failure modes we document, particularly hallucination under RAG in smaller models, remain relevant today.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。