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

Stance detection, the task of predicting an author's viewpoint towards asubject of interest, has long been a focal point of research. Current stancedetection methods predominantly rely on manual annotation of sentences,followed by training a supervised machine learning model. This manualannotation process, however, imposes limitations on the model's ability tofully comprehend the stances in the sentence and hampers its potential togeneralize across different contexts. In this study, we investigate the use ofLarge Language Models (LLMs) for the task of stance classification, with anabsolute minimum use of human labels. We scrutinize four distinct types ofprompting schemes combined with LLMs, comparing their accuracies with manualstance determination. Our study reveals that while LLMs can match or sometimeseven exceed the benchmark results in each dataset, their overall accuracy isnot definitively better than what can be produced by supervised models. Thissuggests potential areas for improvement in the stance classification for LLMs.The application of LLMs, however, opens up promising avenues for unsupervisedstance detection, thereby curtailing the need for manual collection andannotation of stances. This not only streamlines the process but also paves theway for expanding stance detection capabilities across languages. Through thispaper, we shed light on the stance classification abilities of LLMs, therebycontributing valuable insights that can guide future advancements in thisdomain.

Use of Large Language Models for Stance Classification