Paper: arXiv 2405.14767
Authors: Hongyang Yang, Boyu Zhang, Neng Wang, Cheng Guo, Xiaoli Zhang, Likun Lin, Junlin Wang, Tianyu Zhou, Mao Guan, Runjia Zhang, Christina Dan Wang
Abstract
As financial institutions and professionals increasingly incorporate Large Language Models (LLMs) into their workflows, substantial barriers, including proprietary data and specialized knowledge, persist between the finance sector and the AI community. These challenges impede the AI community’s ability to enhance financial tasks effectively. Acknowledging financial analysis’s critical role, we aim to devise financial-specialized LLM-based toolchains and democratize access to them through open-source initiatives, promoting wider AI adoption in financial decision-making. In this paper, we introduce FinRobot, a novel open-source AI agent platform supporting multiple financially specialized AI agents, each powered by LLM. Specifically, the platform consists of four major layers: 1) the Financial AI Agents layer that formulates Financial Chain-of-Thought (CoT) by breaking sophisticated financial problems down into logical sequences; 2) the Financial LLM Algorithms layer dynamically configures appropriate model application strategies for specific tasks; 3) the LLMOps and DataOps layer produces accurate models by applying training/fine-tuning techniques and using task-relevant data; 4) the Multi-source LLM Foundation Models layer that integrates various LLMs and enables the above layers to access them directly. Finally, FinRobot provides hands-on for both professional-grade analysts and laypersons to utilize powerful AI techniques for advanced financial analysis. We open-source FinRobot at \url{“https://github.com/AI4Finance-Foundation/FinRobot"}.
Complexity vs Empirical Score
- Math Complexity: 3.5/10
- Empirical Rigor: 6.0/10
- Quadrant: Street Traders — empirical and applied, lower math complexity
Why this score: The paper introduces a modular platform architecture with operational layers rather than heavy mathematical derivations, resulting in moderate complexity. It demonstrates practical implementation with a public GitHub repository and specific evaluation cases, giving it solid empirical grounding for application development.
Research Flowchart
flowchart TD
A["Research Goal: Develop Financial-Specialized LLM Platform"] --> B["Key Methodology: Four-Layer Architecture"]
subgraph B ["Four-Layer Architecture"]
B1["Financial AI Agents<br>Financial CoT Formulation"]
B2["Financial LLM Algorithms<br>Dynamic Model Configuration"]
B3["LLMOps & DataOps<br>Model Training/Fine-tuning"]
B4["Multi-source LLM Foundation<br>Integrated LLM Access"]
end
B --> C["Computational Process: Pipeline Execution"]
C --> D["Key Outcomes: FinRobot Platform"]
D --> D1["Open-Source AI Agent Platform<br>github.com/AI4Finance-Foundation/FinRobot"]
D --> D2["Specialized Financial Analysis<br>For Professional & Layperson Users"]
D --> D3["Democratized Access to Financial AI Tools"]
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes FinRobot, an open-source AI agent platform with four layers that supports multiple financially specialized AI agents powered by large language models.
Source sentence
In this paper, we introduce FinRobot, a novel open-source AI agent platform supporting multiple financially specialized AI agents, each powered by LLM.
Assumes
No explicit assumptions found in the text.
Data
- Finnhub text-news public
Source sentence
This section will give a solid overview of the Market Forecaster targeted at the US stock market and Chinese stock market with data sources Finnhub and EastMoney.
- EastMoney text-news public
Source sentence
This section will give a solid overview of the Market Forecaster targeted at the US stock market and Chinese stock market with data sources Finnhub and EastMoney.
- DOW 30 market-prices public
Source sentence
Model This AI Agent is powered by fine-tuned FinGPT-Forecasters using Llama-2-7b-chat-hf with LoRA, leveraging data from the latest year’s DOW 30 for the US Market and SSE 50 for the Chinese Market to ensure precise forecasts for these ma-jor stocks and demonstrating robust generalization abilities across various stock symbols.
- SSE 50 market-prices public
Source sentence
Model This AI Agent is powered by fine-tuned FinGPT-Forecasters using Llama-2-7b-chat-hf with LoRA, leveraging data from the latest year’s DOW 30 for the US Market and SSE 50 for the Chinese Market to ensure precise forecasts for these ma-jor stocks and demonstrating robust generalization abilities across various stock symbols.
Costs
Not applicable
Finds
No quantified findings extracted.
Checked by others
No other paper in the archive has been found to support or contradict these findings. Coverage is partial, so this is neither replication nor refutation.
19 papers in the archive
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.
Cited References (85)
- Language models are few-shot learners (2020)
- BloombergGPT : A large language model for finance (2023) — link
- FinRL-Meta : Market Environments and Benchmarks for Data-Driven Financial Reinforcement Learning (2022)
- Dynamic Datasets and Market Environments for Financial Reinforcement Learning (2024)
- FinRL : Deep reinforcement learning framework to automate trading in quantitative finance (2021)
- FinRL : A deep reinforcement learning library for automated stock trading in quantitative finance (2020)
- A Practical Machine Learning Approach for Dynamic Stock Recommendation (2018) — link
- LoRA : Low-rank adaptation of large language models (2021)
and 77 more
- QLoRA : Efficient Finetuning of Quantized LLMs (2023) — link
- Finbert: Financial sentiment analysis with pre-trained language models (2019) — link
- Plato-xl: Exploring the large-scale pre-training of dialogue generation (2021) — link
- Bernice: a multilingual pre-trained encoder for Twitter (2022)
- How twitter is changing the nature of financial news discovery (2016)
- Pretrained language models for biomedical and clinical tasks: understanding and extending the state-of-the-art (2020)
- Bert: Pre-training of deep bidirectional transformers for language understanding (2018) — link
- GPT-3: Its nature, scope, limits, and consequences (2020)
- How contextual are contextualized word representations? comparing the geometry of BERT, ELMo, and GPT-2 embeddings (2019) — link
- Attention is All you Need (2017) — link
- Improving language understanding by generative pre-training (2018)
- Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension (2019) — link
- Lamda: Language models for dialog applications (2022) — link
- Good debt or bad debt: Detecting semantic orientations in economic texts (2014)
- Www'18 open challenge: financial opinion mining and question answering (2018)
- Training language models to follow instructions with human feedback (2022)
- When flue meets flang: Benchmarks and large pre-trained language model for financial domain (2022) — link
- FinRED: A Dataset for Relation Extraction in Financial Domain (2022) — link
- Finqa: A dataset of numerical reasoning over financial data (2021) — link
- FinTral: A Family of GPT-4 Level Multimodal Financial Large Language Models (2024) — link
- DocLLM: A layout-aware generative language model for multimodal document understanding (2023) — link
- F in R ead: A Transfer Learning Based Tool to Assess Readability of Definitions of Financial Terms (2021) — link
- Enhancing Financial Sentiment Analysis via Retrieval Augmented Large Language Models — → 2310.04027
- Instruct-FinGPT: Financial Sentiment Analysis by Instruction Tuning of General-Purpose Large Language Models — → 2306.12659
- The rise and potential of large language model based agents: A survey (2023) — link
- Large language models empowered agent-based modeling and simulation: A survey and perspectives (2023) — link
- A survey on large language model based autonomous agents (2023) — link
- FinAgent: A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist — → 2402.18485
- FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design — → 2311.13743
- Musicagent: An ai agent for music understanding and generation with large language models (2023) — link
- Large language models in medicine (2023)
- Medagents: Large language models as collaborators for zero-shot medical reasoning (2023) — link
- Taskweaver: A code-first agent framework (2023) — link
- Codepori: Large scale model for autonomous software development by using multi-agents (2024) — link
- Can a GPT4-Powered AI Agent Be a Good Enough Performance Attribution Analyst? — → 2403.10482
- Voyager: An open-ended embodied agent with large language models (2023) — link
- AutoGPT (2023)
- LangChain (2022) — link
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework (2023) — link
- MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework (2023) — link
- Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face (2024)
- Cognitive architectures for language agents (2023) — link
- Generative agents: Interactive simulacra of human behavior (2023)
- Communicative Agents for Software Development (2023) — link
- Dify (2024)
- Large language models for robotics: A survey (2023) — link
- Agent ai: Surveying the horizons of multimodal interaction (2024) — link
- Financial intelligence, revised edition: A manager’s guide to knowing what the numbers really mean (2013)
- Sentiment analysis algorithms and applications: A survey (2014)
- Literature review: Machine learning techniques applied to financial market prediction (2019)
- Deep learning for stock market prediction (2020)
- A systematic review of stock market prediction using machine learning and statistical techniques (2022)
- Applications of deep learning in stock market prediction: recent progress (2021)
- FinGPT: Open-Source Financial Large Language Models — → 2306.06031
- Big Data: Deep Learning for financial sentiment analysis (2018)
- FinBERT: A large language model for extracting information from financial text (2023)
- Value Investing: From Graham to Buffett and Beyond (2004) — link
- Accounting for Value (2010) — link
- Chain-of-thought prompting elicits reasoning in large language models (2022)
- Ai in finance: challenges, techniques, and opportunities (2022)
- Artificial intelligence techniques in finance and financial markets: a survey of the literature (2021)
- Temporal Data Meets LLM–Explainable Financial Time Series Forecasting — → 2306.11025
- FinGPT: Instruction Tuning Benchmark for Open-Source Large Language Models in Financial Datasets — → 2310.04793
- Data-centric FinGPT: Democratizing Internet-scale Data for Financial Large Language Models (2023)
- Technical analysis of the financial markets: A comprehensive guide to trading methods and applications (1999)
- Fundamental analysis, future earnings, and stock prices (1997)
- Application of big data with fintech in financial services (2021)
- Harnessing LLMs for temporal data-a study on explainable financial time series forecasting (2023)
- Deep reinforcement learning for automated stock trading: An ensemble strategy (2020)
- LLaMA 2 : Open Foundation and Fine-Tuned Chat Models (2023)
- Glm-130b: An open bilingual pre-trained model (2022) — link
- Falcon-40B : an open large language model with state-of-the-art performance (2023)
- Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs (2024) — link
- What Are Tools Anyway? A Survey from the Language Model Perspective (2024) — link
- MTEB: Massive Text Embedding Benchmark (2022) — link
- ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models (2024) — link
- Financial Statement Analysis with Large Language Models — → 2407.17866
9 of 85 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.