all AI news
Down the Toxicity Rabbit Hole: A Novel Framework to Bias Audit Large Language Models
April 2, 2024, 7:52 p.m. | Arka Dutta, Adel Khorramrouz, Sujan Dutta, Ashiqur R. KhudaBukhsh
cs.CL updates on arXiv.org arxiv.org
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, …
abstract arxiv audit bias cs.cl cs.cy framework identity language language models large language large language models novel paper rabbit set toxicity type
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Business Data Scientist, gTech Ads
@ Google | Mexico City, CDMX, Mexico
Lead, Data Analytics Operations
@ Zocdoc | Pune, Maharashtra, India