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

We introduce FinTral, a suite of state-of-theart multimodal large language models (LLMs) built upon the Mistral-7b model and tailored for financial analysis. FinTral integrates textual, numerical, tabular, and image data. We present FinSet, the largest financial LLM pretraining training, instruction tuning and financial alignment dataset and evaluation benchmark featuring nine tasks and 23 datasets and the first to understand and mitigate financial hallucinations. 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. We also 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 zeroshot 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 decisionmaking in diverse financial contexts. The GitHub repository for FinTral is available at https://github.com/UBC-NLP/fintral.