Applying LLMs to Active Learning: Towards Cost-Efficient Cross-Task Text Classification without Manually Labeled Data

TL;DR

This paper introduces a cost-effective method that combines large language models with active learning to perform cross-task text classification without manual labels, maintaining high accuracy while significantly reducing costs.

Contribution

The study presents a novel approach integrating LLMs into active learning, achieving high cross-task performance without manual annotations and reducing computational costs.

Findings

Achieves over 93% of GPT classification performance

Requires only about 6% of the computational and monetary cost

Enables cost-efficient, high-performance text classification without manual labels

Abstract

Machine learning-based classifiers have been used for text classification, such as sentiment analysis, news classification, and toxic comment classification. However, supervised machine learning models often require large amounts of labeled data for training, and manual annotation is both labor-intensive and requires domain-specific knowledge, leading to relatively high annotation costs. To address this issue, we propose an approach that integrates large language models (LLMs) into an active learning framework, achieving high cross-task text classification performance without the need for any manually labeled data. Furthermore, compared to directly applying GPT for classification tasks, our approach retains over 93% of its classification performance while requiring only approximately 6% of the computational time and monetary cost, effectively balancing performance and resource efficiency. These findings provide new insights into the efficient utilization of LLMs and active learning algorithms in text classification tasks, paving the way for their broader application.