The ability of humans to create and disseminate culture is often credited as the single most
important factor of our success as a species. In this Perspective, we explore the notion of …

Recently, the emergence of pre-trained models (PTMs) has brought natural language
processing (NLP) to a new era. In this survey, we provide a comprehensive review of PTMs …

In this paper, we identify and characterize the emerging area of representation engineering
(RepE), an approach to enhancing the transparency of AI systems that draws on insights …

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 …

Collecting data is one of the bottlenecks of Human-Computer Interaction (HCI) research.
Motivated by this, we explore the potential of large language models (LLMs) in generating …

The capabilities of large language models (LLMs) have sparked debate over whether such
systems just learn an enormous collection of superficial statistics or a set of more coherent …

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 …

Large-scale pre-trained models (PTMs) such as BERT and GPT have recently achieved
great success and become a milestone in the field of artificial intelligence (AI). Owing to …

Gabriel Goh: Research lead. Gabriel Goh first discovered multimodal neurons, sketched out
the project direction and paper outline, and did much of the conceptual and engineering …

Topic modeling is used for discovering latent semantic structure, usually referred to as
topics, in a large collection of documents. The most widely used methods are Latent Dirichlet …