Large language models (LLMs) are one of the most impressive achievements of artificial
intelligence in recent years. However, their relevance to the study of language more broadly …

Large language models (LLMs) have shown powerful performance and development
prospect and are widely deployed in the real world. However, LLMs can capture social …

As machine learning methods are deployed in real-world settings such as healthcare, legal
systems, and social science, it is crucial to recognize how they shape social biases and …

Human-like biases and undesired social stereotypes exist in large pretrained language
models. Given the wide adoption of these models in real-world applications, mitigating such …

Abstract Concept erasure aims to remove specified features from a representation. It can
improve fairness (eg preventing a classifier from using gender or race) and interpretability …

Trust is a central component of the interaction between people and AI, in that'incorrect'levels
of trust may cause misuse, abuse or disuse of the technology. But what, precisely, is the …

A fundamental goal of scientific research is to learn about causal relationships. However,
despite its critical role in the life and social sciences, causality has not had the same …

We survey 146 papers analyzing" bias" in NLP systems, finding that their motivations are
often vague, inconsistent, and lacking in normative reasoning, despite the fact that …

Abstract⚠ This paper contains prompts and model outputs that are offensive in nature. When
trained on large, unfiltered crawls from the Internet, language models pick up and reproduce …

Obtaining human-interpretable explanations of large, general-purpose language models is
an urgent goal for AI safety. However, it is just as important that our interpretability methods …