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 have shown excellent results in few-shot learningscenarios using in-context learning. Although it is impressive, the size oflanguage models can be prohibitive to make them usable in on-deviceapplications, such as sensors or smartphones. With smaller language models,task-specific data annotation is needed to fine-tune the language model for aspecific purpose. However, data annotation can have a substantial financial andtime burden for small research groups, startups, and even companies. In thispaper, we analyze different prompt-based fine-tuning techniques to improveresults on both language and multimodal causal transformer models. To evaluateour results, we use a dataset focusing on visual commonsense reasoning in time.Our results show that by simple model-agnostic prompt-based fine-tuning,comparable results can be reached by only using 35%-40% of the fine-tuningtraining dataset. The proposed approaches result in significant time andfinancial savings. As the proposed methods make minimal architecturalassumptions, other researchers can use the results in their transformer modelswith minimal adaptations. We plan to release the source code freely to make iteasier for the community to use and contribute to our work.

Super-Prompting: Utilizing Model-Independent Contextual Data to Reduce Data Annotation Required in Visual Commonsense Tasks