Large Language Models (LLMs) went from non-existent to ubiquitous in the machine
learning discourse within a few years. Due to the fast pace of the field, it is difficult to identify …

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 …

Widely used alignment techniques, such as reinforcement learning from human feedback
(RLHF), rely on the ability of humans to supervise model behavior-for example, to evaluate …

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 …

Advanced AI models hold the promise of tremendous benefits for humanity, but society
needs to proactively manage the accompanying risks. In this paper, we focus on what we …

The impressive performance of recent language models across a wide range of tasks
suggests that they possess a degree of abstract reasoning skills. Are these skills general …

One widely cited barrier to the adoption of LLMs as proxies for humans in subjective tasks is
their sensitivity to prompt wording—but interestingly, humans also display sensitivities to …

Large language models (LLMs) are currently at the forefront of intertwining AI systems with
human communication and everyday life. Due to rapid technological advances and their …

The widespread adoption of large language models (LLMs) makes it important to recognize
their strengths and limitations. We argue that in order to develop a holistic understanding of …

Human commonsense understanding of the physical and social world is organized around
intuitive theories. These theories support making causal and moral judgments. When …