Researchers at George Washington University explored the use of Large Language Models (LLMs) for automating financial news summarization in Fall 2023. They developed a pipeline integrating news articles, company data from Wikipedia, and stock prices from Yahoo Finance, converting numerical stock data into natural language narratives. The study tested summarization approaches like Summarize Chains and Retrieval-Augmented Generation (RAG) using models such as Falcon-7B-Instruct and GPT (text-davinci-003). Falcon-7B with Summarize Chains yielded the best results, accurately and coherently summarizing news events, while RAG showed issues with repetition and hallucination in smaller models. AI
IMPACT This research highlights potential LLM applications in finance, while also noting limitations like hallucination in RAG models.
RANK_REASON Academic paper detailing an empirical study on LLM summarization techniques.
Read on arXiv cs.IR (Information Retrieval) →
- Apple Inc.
- BART-Large-XSum
- Defense Counterintelligence and Security Agency
- DistilBART-CNN-12-6
- Faiss
- Falcon-7B-Instruct
- George Washington University
- GOOGL
- GPT (text-davinci-003)
- JPMorgan Chase
- Large Language Models
- Meta*
- Microsoft
- News API
- NVDA
- Tesla
- Wikipedia
- Yahoo Finance
- Retrieval-Augmented Generation
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
