Learning with limited labelled data, such as prompting, in-context learning, fine-tuning, meta-
learning, or few-shot learning, aims to effectively train a model using only a small amount of …

Abstract Large Language Models (LLMs) have recently gained significant attention due to
their remarkable capabilities in performing diverse tasks across various domains. However …

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 …

AI progress is creating a growing range of risks and opportunities, but it is often unclear how
they should be navigated. In many cases, the barriers and uncertainties faced are at least …

The rapid development of Large Language Models (LLMs) has called for robust benchmarks
to assess their abilities, track progress, and compare iterations. While existing benchmarks …

There is widespread optimism that frontier Large Language Models (LLMs) and LLM-
augmented systems have the potential to rapidly accelerate scientific discovery across …

Test-time interventions for language models can enhance factual accuracy, mitigate harmful
outputs, and improve model efficiency without costly retraining. But despite a flood of new …

Foundation model development attracts a rapidly expanding body of contributors, scientists,
and applications. To help shape responsible development practices, we introduce the …

LLM (large language model) practitioners commonly notice that outputs can vary for the
same inputs, but we have been unable to find work that evaluates LLM stability as the main …

AI models are increasingly prevalent in high-stakes environments, necessitating thorough
assessment of their capabilities and risks. Benchmarks are popular for measuring these …