Large Language Models (LLMs), consisting of 100 billion or more parameters, have demonstrated remarkable ability in complex multi-step reasoning tasks. However, the application of such generic advancements has been limited to a few fields, such as clinical or legal, with the field of financial reasoning remaining largely unexplored. To the best of our knowledge, the ability of LLMs to solve financial reasoning problems has never been dealt with, and whether it can be performed at any scale remains unknown. To address this knowledge gap, this research presents a comprehensive investigation into the potential application of LLMs in the financial domain. The investigation includes a detailed exploration of a range of subjects, including task formulation, synthetic data generation, prompting methods, and evaluation capability. Furthermore, the study benchmarks various GPT variants with parameter scales ranging from 2.8B to 13B, with and without instruction tuning, on diverse dataset sizes. By analyzing the results, we reveal that the ability to generate coherent financial reasoning first emerges at 6B parameters, and continues to improve with better instruction-tuning or larger datasets. Additionally, the study provides a publicly accessible dataset named sFIOG (Synthetic-Financial Investment Opinion Generation), consisting of 11,802 synthetic investment thesis samples, to support further research in the field of financial reasoning. Overall, this research seeks to contribute to the understanding of the efficacy of language models in the field of finance, with a particular emphasis on their ability to engage in sophisticated reasoning and analysis within the context of investment decision-making.

翻译：大语言模型（LLMs），包含1000亿或更多参数，已在复杂多步骤推理任务中展现出卓越能力。然而，此类通用进展的应用仅限于临床、法律等少数领域，而金融推理领域在很大程度上仍未被探索。据我们所知，LLMs解决金融推理问题的能力迄今未得到系统研究，且其是否能在任何规模下实现尚属未知。为填补这一知识空白，本研究对LLMs在金融领域的潜在应用进行了全面调查，涵盖任务制定、合成数据生成、提示方法及评估能力等一系列主题的详细探索。此外，研究在不同规模数据集上对参数范围从28亿到130亿的各种GPT变体进行基准测试（包括经指令微调与未经指令微调的情况）。通过分析结果，我们发现生成连贯金融推理的能力首次在60亿参数规模显现，并随改进的指令微调或更大数据集而持续提升。同时，本研究提供了公开数据集sFIOG（合成金融投资观点生成），包含11802个合成投资主题样本，以支持金融推理领域的进一步研究。总体而言，本研究旨在增进对语言模型在金融领域效力的理解，特别关注其在投资决策背景下进行复杂推理与分析的能力。