Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM
Abstract
The remarkable performance of large language models (LLMs) in zero-shot language understanding has garnered significant attention. However, employing LLMs for large-scale inference or domain-specific fine-tuning requires immense computational resources due to their substantial model size. To overcome these limitations, we introduce a novel method, namely GenCo, which leverages the strong generative power of LLMs to assist in training a smaller and more adaptable language model. In our method, an LLM plays an important role in the self-training loop of a smaller model in two important ways. Firstly, the LLM is used to augment each input instance with a variety of possible continuations, enriching its semantic context for better understanding. Secondly, it helps crafting additional high-quality training pairs, by rewriting input texts conditioned on predicted labels. This ensures the generated texts are highly relevant to the predicted labels, alleviating the prediction error during pseudo-labeling, while reducing the dependency on large volumes of unlabeled text. In our experiments, GenCo outperforms previous state-of-the-art methods when only limited ( of original) in-domain text data is available. Notably, our approach surpasses the performance of Alpaca-7B with human prompts, highlighting the potential of leveraging LLM for self-training.
Cite
@article{arxiv.2304.11872,
title = {Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM},
author = {Ruohong Zhang and Yau-Shian Wang and Yiming Yang},
journal= {arXiv preprint arXiv:2304.11872},
year = {2024}
}