Conversational large language models are fine-tuned for both instruction-following and
safety, resulting in models that obey benign requests but refuse harmful ones. While this …

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 …

Humans are capable of strategically deceptive behavior: behaving helpfully in most
situations, but then behaving very differently in order to pursue alternative objectives when …

Refusal training is widely used to prevent LLMs from generating harmful, undesirable, or
illegal outputs. We reveal a curious generalization gap in the current refusal training …

Jailbreak attacks cause large language models (LLMs) to generate harmful, unethical, or
otherwise objectionable content. Evaluating these attacks presents a number of challenges …

Large Language Models (LLMs) have become prevalent across diverse sectors,
transforming human life with their extraordinary reasoning and comprehension abilities. As …

The advancement of Large Language Models (LLMs) has significantly impacted various
domains, including Web search, healthcare, and software development. However, as these …

Achieving a mechanistic understanding of transformer-based language models is an open
challenge, especially due to their large number of parameters. Moreover, the lack of ground …

Large Language Models (LLMs) demonstrate outstanding performance in their reservoir of
knowledge and understanding capabilities, but they have also been shown to be prone to …

Large language models (LLMs) are being rapidly developed, and a key component of their
widespread deployment is their safety-related alignment. Many red-teaming efforts aim to …