Large Language Models (LLMs) have performed exceptionally in various text-generative
tasks, including question answering, translation, code completion, etc. However, the over …

This is the interim publication of the first International Scientific Report on the Safety of
Advanced AI. The report synthesises the scientific understanding of general-purpose AI--AI …

The rapid evolution of artificial intelligence (AI) through developments in Large Language
Models (LLMs) and Vision-Language Models (VLMs) has brought significant advancements …

Today's LLMs are susceptible to prompt injections, jailbreaks, and other attacks that allow
adversaries to overwrite a model's original instructions with their own malicious prompts. In …

Large language models (LLMs) have transformed the development of embodied
intelligence. By providing a few contextual demonstrations, developers can utilize the …

In this paper, we explore the capabilities of state-of-the-art large language models (LLMs)
such as GPT-4, Claude 3 Opus, and Gemini 1.0 Ultra in solving undergraduate-level control …

Large language models (LLMs) have achieved unprecedented success in the field of natural
language processing. However, the black-box nature of their internal mechanisms has …

Large language models (LLMs) are trained on a deluge of text data with limited quality
control. As a result, LLMs can exhibit unintended or even harmful behaviours, such as …

Large language models (LLMs) trained on web-scale datasets raise substantial concerns
regarding permissible data usage. One major question is whether these models" memorize" …

A plethora of jailbreaking attacks have been proposed to obtain harmful responses from
safety-tuned LLMs. In their original settings, these methods all largely succeed in coercing …