4 accepted papers
Auditing large language models (LLMs) for biases is an ongoing and dynamic process, resembling a proverbial cat-and-mouse game. As researchers identify new vulnerabilities in LLMs, guardrails are updated to address them, prompting the need for innovative approaches to audit the increasingly fortifie
This paper makes a novel combination of a recently proposed bias audit framework and a recently proposed jailbreaking technique for Llama3. On an audit comprising several disadvantaged groups, our experiments reveal that a jailbroken Llama3 exhibits worrisome antisemitism, racism, misogyny, and homo…
Human input plays a critical role in modern AI systems. As machines take on increasingly nuanced tasks, it becomes essential for the community to embrace subjectivity and diverse perspectives. However, research on sensitive topics often fails to incorporate diverse and balanced perspectives. This pa
This paper makes three contributions. First, it presents a generalizable, novel framework dubbed 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 PaLM 2 guardrails present…