FinTral：一系列 GPT-4 級別的多模態金融大型語言模型

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

February 16, 2024

作者: Gagan Bhatia, El Moatez Billah Nagoudi, Hasan Cavusoglu, Muhammad Abdul-Mageed

cs.AI

摘要

我們介紹了 FinTral，這是一套基於 Mistral-7b 模型打造、專為金融分析量身定制的最先進多模式大型語言模型（LLMs）套件。FinTral 整合了文本、數值、表格和圖像數據。我們通過利用我們為此工作精心策劃的大量文本和視覺數據集，為 FinTral 增添了特定領域的預訓練、指導微調和 RLAIF 訓練。我們還推出了一個包含九個任務和 25 個數據集的廣泛基準，其中包括金融領域的幻覺。我們的 FinTral 模型採用直接偏好優化進行訓練，並應用先進的工具和檢索方法，被稱為 FinTral-DPO-T&R，展現出卓越的零-shot性能。它在所有任務中均優於 ChatGPT-3.5，並在九個任務中的五個中超越了 GPT-4，標誌著人工智慧驅動金融技術的重大進步。我們還展示了 FinTral 在不同金融情境下實時分析和決策方面具有出色潛力。

English

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.