Hundreds of millions of people now interact with language models, with uses ranging from
help with writing, to informing hiring decisions. However, these language models are known …

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 …

Without proper safeguards, large language models will readily follow malicious instructions
and generate toxic content. This risk motivates safety efforts such as red-teaming and large …

Large Language Models (LLMs) have demonstrated exceptional task-solving capabilities,
increasingly adopting roles akin to human-like assistants. The broader integration of LLMs …

Large language models (LLMs) appear to bias their survey answers toward certain values.
Nonetheless, some argue that LLMs are too inconsistent to simulate particular values. Are …

While large language models (LLMs) present significant potential for supporting numerous
real-world applications and delivering positive social impacts, they still face significant …

How could LLMs influence our democracy? We investigate LLMs' political leanings and the
potential influence of LLMs on voters by conducting multiple experiments in a US …

As modern AI models become integral to everyday tasks, concerns about their inherent
biases and their potential impact on human decision-making have emerged. While bias in …

Uncovering latent values and opinions embedded in large language models (LLMs) can
help identify biases and mitigate potential harm. Recently, this has been approached by …

Benchmarks and leaderboards are commonly used to track the fairness impacts of artificial
intelligence (AI) models. Many critics argue against this practice, since it incentivizes …