FinBloom: Knowledge Grounding Large Language Model with Real-time Financial Data

TL;DR

FinBloom introduces a specialized 7B parameter language model fine-tuned on financial data, enabling real-time, context-aware financial query answering and decision-making with reduced latency.

Contribution

We developed FinBloom 7B, a financial domain-specific LLM fine-tuned on extensive financial news and filings, and created a dataset for real-time financial query context understanding.

Findings

Enhanced real-time financial query answering capabilities.

Significant reduction in data retrieval latency.

Improved performance in dynamic financial tasks.

Abstract

Large language models (LLMs) excel at generating human-like responses but often struggle with interactive tasks that require access to real-time information. This limitation poses challenges in finance, where models must access up-to-date information, such as recent news or price movements, to support decision-making. To address this, we introduce Financial Agent, a knowledge-grounding approach for LLMs to handle financial queries using real-time text and tabular data. Our contributions are threefold: First, we develop a Financial Context Dataset of over 50,000 financial queries paired with the required context. Second, we develop FinBloom 7B, a custom 7 billion parameter LLM, by fine-tuning Bloom 7B on 14 million financial news articles from Reuters and Deutsche Presse-Agentur (DPA), alongside a random sample of 25% from 12 million Securities and Exchange Commission (SEC) filings. Third, we fine-tune FinBloom 7B using the Financial Context Dataset to serve as a Financial Agent. This agent generates relevant financial context, enabling efficient real-time data retrieval to answer user queries. By reducing latency and eliminating the need for users to manually provide accurate data, our approach significantly enhances the capability of LLMs to handle dynamic financial tasks. Our proposed approach makes real-time financial decisions, algorithmic trading and other related tasks streamlined, and is valuable in contexts with high-velocity data flows.