FinTral: A Family of GPT-4 Level Multimodal Financial Large Language Models
This work addresses the need for advanced AI-driven financial technology by providing a domain-specific model with competitive performance, though it is incremental as it builds upon existing models like Mistral-7b.
The authors tackled the problem of financial analysis by developing FinTral, a suite of multimodal large language models that integrate textual, numerical, tabular, and image data, resulting in a model that outperforms ChatGPT-3.5 in all tasks and surpasses GPT-4 in five out of nine tasks.
We introduce FinTral, a suite of state-of-the-art 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 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 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. The GitHub repository for FinTral is available at \url{https://github.com/UBC-NLP/fintral}.