The reviewed record of science sign in
Pith

arxiv: 2304.11872 · v2 · pith:K3E3DYPK · submitted 2023-04-24 · cs.CL · cs.AI

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

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:K3E3DYPKrecord.jsonopen to challenge →

classification cs.CL cs.AI
keywords languagellmsmodelself-trainingtextgencoimportantinput
0
0 comments X
read the original 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 ($<5\%$ 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.