Breaking the Bank with ChatGPT: Few-Shot Text Classification for Finance

by   Lefteris Loukas, et al.

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.


Guiding Generative Language Models for Data Augmentation in Few-Shot Text Classification

Data augmentation techniques are widely used for enhancing the performan...

Myers-Briggs personality classification from social media text using pre-trained language models

In Natural Language Processing, the use of pre-trained language models h...

Label Semantic Aware Pre-training for Few-shot Text Classification

In text classification tasks, useful information is encoded in the label...

Towards Agile Text Classifiers for Everyone

Text-based safety classifiers are widely used for content moderation and...

Few-shot Text Classification with Dual Contrastive Consistency

In this paper, we explore how to utilize pre-trained language model to p...

In-Context Learning for Text Classification with Many Labels

In-context learning (ICL) using large language models for tasks with man...

UniHD at TSAR-2022 Shared Task: Is Compute All We Need for Lexical Simplification?

Previous state-of-the-art models for lexical simplification consist of c...

Please sign up or login with your details

Forgot password? Click here to reset