Recent research has shown that smaller language models can acquire substantial reasoning abilities when fine-tuned with reasoning exemplars crafted by a significantly larger teacher model. We explore this paradigm for the financial domain, focusing on the challenge of answering questions that require multi-hop numerical reasoning over financial texts. We assess the performance of several smaller models that have been fine-tuned to generate programs that encode the required financial reasoning and calculations. Our findings demonstrate that these fine-tuned smaller models approach the performance of the teacher model. To provide a granular analysis of model performance, we propose an approach to investigate the specific student model capabilities that are enhanced by fine-tuning. Our empirical analysis indicates that fine-tuning refines the student models ability to express and apply the required financial concepts along with adapting the entity extraction for the specific data format. In addition, we hypothesize and demonstrate that comparable financial reasoning capability can be induced using relatively smaller datasets.

翻译：近期研究表明，当使用由显著更大的教师模型生成的推理示例进行微调时，小型语言模型能够获得实质性的推理能力。我们在金融领域探索这一范式，重点关注需要对金融文本进行多跳数值推理的问答任务。我们评估了多个经过微调的小型模型性能，这些模型被训练用于生成编码所需金融推理与计算过程的程序。研究结果表明，经过微调的小型模型能够接近教师模型的性能水平。为提供细粒度的模型性能分析，我们提出了一种方法来探究微调所增强的学生模型具体能力。实证分析表明，微调优化了学生模型表达与应用所需金融概念的能力，同时使其实体提取功能适应特定数据格式。此外，我们提出并验证了可通过相对较小的数据集诱导出可比拟的金融推理能力这一假设。