The Fin AI

Purpose

The rapid advancement of AI in the financial sector brings both opportunities and challenges, particularly in the development and deployment of Large Language Models (LLMs). The Fin AI working group is established to spearhead open science, tooling, and model initiatives, ensuring responsible innovation and application in financial services.

Open Science

Financial AI Research

Open Tooling

Financial AI Development & Analysis

Open Models

Financial AI Application

Key Projects

Our key projects comprehensively cover the lifecycle of financial LLMs, from curating datasets and developing benchmarks to releasing models, creating application frameworks, and optimizing deployment systems. These efforts ensure innovation, transparency, and ethical standards in financial AI.

FinData

Curating comprehensive open-source datasets for pre-training, fine-tuning, and evaluating financial LLMs, addressing the need for diverse and robust data resources.

FinBen

Developing holistic benchmarks incorporating instruction-based, multi-turn, multi-modal, multi-lingual, Retrieval-Augmented Generation (RAG) based, and agent-based evaluations to accurately assess financial LLM performance.

Papers:

Project: https://github.com/The-FinAI/PIXIU

FinModel

Releasing a series of open-source financial LLMs including 1.5B, 8B, and 70B parameter models along with their checkpoints and training scripts, facilitating accessibility and innovation in model development.

Papers:
1. Open-FinLLMs: Open Multimodal Large Language Models for Financial Applications

FinCon

Building a multi-agent collaborative system equipped with human-like cognitive capabilities and quantified dynamic risk profiles, designed to optimize the quality of sequential, multi-turn financial decision-making processes. This innovative system leverages multi-modal financial data inputs, forging a robust link between intelligent system design and behavioral finance principles. It is versatile enough to be employed in a wide range of financial tasks.

Papers:

FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making

FinApp

Creating a federated learning-based application framework for reliable and trustworthy financial LLM applications, emphasizing privacy and security in financial AI deployments.

Papers: