When Machine Learning technologies are used in contexts that affect citizens, companies as
well as researchers need to be confident that there will not be any unexpected social …

AI alignment aims to make AI systems behave in line with human intentions and values. As
AI systems grow more capable, the potential large-scale risks associated with misaligned AI …

In the last year, new models and methods for pretraining and transfer learning have driven
striking performance improvements across a range of language understanding tasks. The …

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 …

Existing public face image datasets are strongly biased toward Caucasian faces, and other
races (eg, Latino) are significantly underrepresented. The models trained from such datasets …

A stereotype is an over-generalized belief about a particular group of people, eg, Asians are
good at math or Asians are bad drivers. Such beliefs (biases) are known to hurt target …

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 …

Rising concern for the societal implications of artificial intelligence systems has inspired a
wave of academic and journalistic literature in which deployed systems are audited for harm …

Generative search engines directly generate responses to user queries, along with in-line
citations. A prerequisite trait of a trustworthy generative search engine is verifiability, ie …

An introduction to the intellectual foundations and practical utility of the recent work on
fairness and machine learning. Fairness and Machine Learning introduces advanced …