Large language models (LLMs) have exhibited an array of reasoning capabilities but face challenges like error propagation and hallucination, particularly in specialised areas like finance, where data is heterogeneous, and precision is paramount. We explore the potential of language model augmentation with external tools to mitigate these limitations and offload certain reasoning steps to external tools that are more suited for the task, instead of solely depending on the LLM's inherent abilities. More concretely, using financial domain question-answering datasets, we apply supervised fine-tuning on a LLaMA-2 13B Chat model to act both as a 'task router' and 'task solver'. The 'task router' dynamically directs a question to either be answered internally by the LLM or externally via the right tool from the tool set. Our tool-equipped SFT model, Raven, demonstrates an improvement of 35.2% and 5.06% over the base model and SFT-only baselines, respectively, and is highly competitive with strong GPT-3.5 results. To the best of our knowledge, our work is the first that investigates tool augmentation of language models for the finance domain.

通过使用外部工具对语言模型进行增强，可缓解传播误差和幻觉等挑战，特别是在数据异构、精确性至关重要的金融领域。我们将监督微调应用于 LLaMA-2 13B Chat 模型，使其成为 '任务路由器' 和 '任务解决器'。通过使用金融领域的问答数据集，我们的模型 Raven 在改进基准模型和仅进行监督微调的基线模型上分别显示了 35.2% 和 5.06% 的改进，并且与 GPT-3.5 取得了很好的竞争效果。据我们所知，这是首个探索对金融领域的语言模型进行工具增强的研究。

为金融中的表格数据分析赋予语言模型工具使用能力