Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Ruohong, Wang, Yau-Shian, Yang, Yiming
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914751781535744
author Zhang, Ruohong
Wang, Yau-Shian
Yang, Yiming
author_facet Zhang, Ruohong
Wang, Yau-Shian
Yang, Yiming
contents 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 ($<5\%$ 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.
format Preprint
id arxiv_https___arxiv_org_abs_2304_11872
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM
Zhang, Ruohong
Wang, Yau-Shian
Yang, Yiming
Computation and Language
Artificial Intelligence
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 ($<5\%$ 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.
title Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2304.11872