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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Prompt engineering relevance research has seen a notable surge in recentyears, primarily driven by advancements in pre-trained language models andlarge language models. However, a critical issue has been identified withinthis domain: the inadequate of sensitivity and robustness of these modelstowards Prompt Templates, particularly in lesser-studied languages such asJapanese. This paper explores this issue through a comprehensive evaluation ofseveral representative Large Language Models (LLMs) and a widely-utilizedpre-trained model(PLM). These models are scrutinized using a benchmark datasetin Japanese, with the aim to assess and analyze the performance of the currentmultilingual models in this context. Our experimental results reveal startlingdiscrepancies. A simple modification in the sentence structure of the PromptTemplate led to a drastic drop in the accuracy of GPT-4 from 49.21 to 25.44.This observation underscores the fact that even the highly performance GPT-4model encounters significant stability issues when dealing with diverseJapanese prompt templates, rendering the consistency of the model's outputresults questionable. In light of these findings, we conclude by proposingpotential research trajectories to further enhance the development andperformance of Large Language Models in their current stage.

Sensitivity and Robustness of Large Language Models to Prompt Template in Japanese Text Classification Tasks