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

Pre-trained language models (LMs) obtain state-of-the-art performance whenadapted to text classification tasks. However, when using such models inreal-world applications, efficiency considerations are paramount. In thispaper, we study how different training procedures that adapt LMs to textclassification perform, as we vary model and train set size. More specifically,we compare standard fine-tuning, prompting, and knowledge distillation (KD)when the teacher was trained with either fine-tuning or prompting. Our findingssuggest that even though fine-tuning and prompting work well to train large LMson large train sets, there are more efficient alternatives that can reducecompute or data cost. Interestingly, we find that prompting combined with KDcan reduce compute and data cost at the same time.

Performance-Efficiency Trade-Offs in Adapting Language Models to Text Classification Tasks