Breaking the Bank with ChatGPT: Few-Shot Text Classification for Finance
This provides a practical solution for financial organizations with limited labeled data, though it's incremental in applying existing methods to a specific domain.
The paper tackles few-shot text classification in finance using GPT models and SetFit fine-tuning, showing that GPT-3.5 and GPT-4 outperform fine-tuned non-generative models with fewer examples and achieve state-of-the-art results on the Banking77 dataset.
We propose the use of conversational GPT models for easy and quick few-shot text classification in the financial domain using the Banking77 dataset. Our approach involves in-context learning with GPT-3.5 and GPT-4, which minimizes the technical expertise required and eliminates the need for expensive GPU computing while yielding quick and accurate results. Additionally, we fine-tune other pre-trained, masked language models with SetFit, a recent contrastive learning technique, to achieve state-of-the-art results both in full-data and few-shot settings. Our findings show that querying GPT-3.5 and GPT-4 can outperform fine-tuned, non-generative models even with fewer examples. However, subscription fees associated with these solutions may be considered costly for small organizations. Lastly, we find that generative models perform better on the given task when shown representative samples selected by a human expert rather than when shown random ones. We conclude that a) our proposed methods offer a practical solution for few-shot tasks in datasets with limited label availability, and b) our state-of-the-art results can inspire future work in the area.