FinTral: A Family of GPT-4 Level Multimodal Financial Large Language Models

Anonymous

Abstract: We introduce FinTral, a suite of state-of-the-art multimodal large language models (LLMs) built upon the Mistral-7b model and tailoredfor financial analysis. FinTral integrates textual, numerical, tabular, and image data. We enhance FinTral with domain-specific pretraining, instruction fine-tuning, and RLAIF training by exploiting a large collection of textual and visual datasets we curate for this work. Wealso introduce an extensive benchmark featuring nine tasks and 25 datasets for evaluation, including hallucinations in the financial domain. Our FinTral model trained with direct preference optimization employing advanced Tools and Retrieval methods, dubbed FinTral-DPO-T&R, demonstrates an exceptional zero-shot performance. It outperforms ChatGPT-3.5 in all tasks and surpasses GPT-4 in five out of nine tasks, marking a significant advancement in AI-driven financial technology. We also demonstrate that FinTral has the potential to excel in real-time analysis and decision-making in diverse financial contexts.

Paper Type: long

Research Area: Interpretability and Analysis of Models for NLP

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Approaches low compute settings-efficiency, Publicly available software and/or pre-trained models, Data resources

Languages Studied: English