AI alignment aims to make AI systems behave in line with human intentions and values. As
AI systems grow more capable, the potential large-scale risks associated with misaligned AI …

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 …

Because" out-of-the-box" large language models are capable of generating a great deal of
objectionable content, recent work has focused on aligning these models in an attempt to …

Large language models trained for safety and harmlessness remain susceptible to
adversarial misuse, as evidenced by the prevalence of “jailbreak” attacks on early releases …

Large language models are now tuned to align with the goals of their creators, namely to be"
helpful and harmless." These models should respond helpfully to user questions, but refuse …

The rapid progress in open-source large language models (LLMs) is significantly advancing
AI development. Extensive efforts have been made before model release to align their …

This work identifies 18 foundational challenges in assuring the alignment and safety of large
language models (LLMs). These challenges are organized into three different categories …

Warning: this paper contains data, prompts, and model outputs that are offensive in nature.
Recently, there has been a surge of interest in integrating vision into Large Language …

Safety lies at the core of the development of Large Language Models (LLMs). There is
ample work on aligning LLMs with human ethics and preferences, including data filtering in …

Most traditional AI safety research has approached AI models as machines and centered on
algorithm-focused attacks developed by security experts. As large language models (LLMs) …