For a long time, researchers have sought artificial intelligence (AI) that matches or exceeds
human intelligence. AI agents, which are artificial entities capable of sensing the …

Large Language Models (LLMs) are swiftly advancing in architecture and capability, and as
they integrate more deeply into complex systems, the urgency to scrutinize their security …

Abstract Generative Pre-trained Transformer (GPT) models have exhibited exciting progress
in their capabilities, capturing the interest of practitioners and the public alike. Yet, while the …

Abstract While Large Language Models (LLMs) display versatile functionality, they continue
to generate harmful, biased, and toxic content, as demonstrated by the prevalence of human …

Despite efforts to align large language models (LLMs) with human intentions, widely-used
LLMs such as GPT, Llama, and Claude are susceptible to jailbreaking attacks, wherein an …

Automated red teaming holds substantial promise for uncovering and mitigating the risks
associated with the malicious use of large language models (LLMs), yet the field lacks a …

The increasing reliance on Large Language Models (LLMs) across academia and industry
necessitates a comprehensive understanding of their robustness to prompts. In response to …

Recently, Large Language Models (LLMs) have made significant advancements and are
now widely used across various domains. Unfortunately, there has been a rising concern …

This paper reexamines the research on out-of-distribution (OOD) robustness in the field of
NLP. We find that the distribution shift settings in previous studies commonly lack adequate …

External audits of AI systems are increasingly recognized as a key mechanism for AI
governance. The effectiveness of an audit, however, depends on the degree of access …