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

Abstract

This paper makes three contributions. First, it presents a generalizable, novel framework dubbed \textit{toxicity rabbit hole} that iteratively elicits toxic content from a wide suite of large language models. Spanning a set of 1,266 identity groups, we first conduct a bias audit of \texttt{PaLM 2} guardrails presenting key insights. Next, we report generalizability across several other models. Through the elicited toxic content, we present a broad analysis with a key emphasis on racism, antisemitism, misogyny, Islamophobia, homophobia, and transphobia. Finally, driven by concrete examples, we discuss potential ramifications.