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/

Zendy Plus

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

Zendy Tools

Zendy Open

This paper makes three contributions. First, it presents a generalizable,novel framework dubbed \textit{toxicity rabbit hole} that iteratively elicitstoxic content from a wide suite of large language models. Spanning a set of1,266 identity groups, we first conduct a bias audit of \texttt{PaLM 2}guardrails presenting key insights. Next, we report generalizability acrossseveral other models. Through the elicited toxic content, we present a broadanalysis with a key emphasis on racism, antisemitism, misogyny, Islamophobia,homophobia, and transphobia. Finally, driven by concrete examples, we discusspotential ramifications.

Down the Toxicity Rabbit Hole: A Novel Framework to Bias Audit Large Language Models