English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Training or finetuning large-scale language models (LLMs) such as GPT-3requires substantial computation resources, motivating recent efforts toexplore parameter-efficient adaptation to downstream tasks. One practical areaof research is to treat these models as black boxes and interact with themthrough their inference APIs. In this paper, we investigate how to optimizefew-shot text classification without accessing the gradients of the LLMs. Toachieve this, we treat the black-box model as a feature extractor and train aclassifier with the augmented text data. Data augmentation is performed usingprompt-based finetuning on an auxiliary language model with a much smallerparameter size than the black-box model. Through extensive experiments on eighttext classification datasets, we show that our approach, dubbed BT-Classifier,significantly outperforms state-of-the-art black-box few-shot learners andperforms on par with methods that rely on full-model tuning.

Enhancing Black-Box Few-Shot Text Classification with Prompt-Based Data Augmentation