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

Controversy is a reflection of our zeitgeist, and an important aspect to anydiscourse. The rise of large language models (LLMs) as conversational systemshas increased public reliance on these systems for answers to their variousquestions. Consequently, it is crucial to systematically examine how thesemodels respond to questions that pertaining to ongoing debates. However, fewsuch datasets exist in providing human-annotated labels reflecting thecontemporary discussions. To foster research in this area, we propose a novelconstruction of a controversial questions dataset, expanding upon the publiclyreleased Quora Question Pairs Dataset. This dataset presents challengesconcerning knowledge recency, safety, fairness, and bias. We evaluate differentLLMs using a subset of this dataset, illuminating how they handle controversialissues and the stances they adopt. This research ultimately contributes to ourunderstanding of LLMs' interaction with controversial issues, paving the wayfor improvements in their comprehension and handling of complex societaldebates.

DELPHI: Data for Evaluating LLMs' Performance in Handling Controversial Issues