AI systems are becoming increasingly intertwined with human life. In order to effectively
collaborate with humans and ensure safety, AI systems need to be able to understand …

This survey summarises the most recent methods for building and assessing helpful, honest,
and harmless neural language models, considering small, medium, and large-size models …

To explain why an action is wrong, we sometimes say,“What if everybody did that?” In other
words, even if a single person's behavior is harmless, that behavior may be wrong if it would …

It is widely agreed upon that morality guides people with conflicting interests towards
agreements of mutual benefit. We therefore might expect numerous proposals for organizing …

Constraining the actions of AI systems is one promising way to ensure that these systems
behave in a way that is morally acceptable to humans. But constraints alone come with …

People can instantaneously create novel conventions that link individual communicative
signals to meanings, both in experiments and everyday communication. Yet a basic …

Moral or ethical judgments rely heavily on the specific contexts in which they occur.
Understanding varying shades of defeasible contextualizations (ie, additional information …

I argue that our general disposition to make moral judgments and our core moral intuitions
are likely the product of social selection—a kind of gene–culture coevolution driven by the …

In this survey, we provide a systematic review of recent work on modelling morality in text, an
area of research that has garnered increasing attention in recent years. Our survey is …

People sometimes display moral flexibility by deciding that a commonly accepted moral
norm ought not to apply in particular circumstances. But how? We explore this question in …