DeepAI AI Chat
Log In Sign Up

Learning Norms via Natural Language Teachings

by   Taylor Olson, et al.

To interact with humans, artificial intelligence (AI) systems must understand our social world. Within this world norms play an important role in motivating and guiding agents. However, very few computational theories for learning social norms have been proposed. There also exists a long history of debate on the distinction between what is normal (is) and what is normative (ought). Many have argued that being capable of learning both concepts and recognizing the difference is necessary for all social agents. This paper introduces and demonstrates a computational approach to learning norms from natural language text that accounts for both what is normal and what is normative. It provides a foundation for everyday people to train AI systems about social norms.


page 1

page 2

page 3

page 4


Engaging in Dialogue about an Agent's Norms and Behaviors

We present a set of capabilities allowing an agent planning with moral a...

Bayesian Inference of Social Norms as Shared Constraints on Behavior

People act upon their desires, but often, also act in adherence to impli...

Linking sanctions to norms in practice

Within social simulation, we often want agents to interact both with lar...

In conversation with Artificial Intelligence: aligning language models with human values

Large-scale language technologies are increasingly used in various forms...

NormBank: A Knowledge Bank of Situational Social Norms

We present NormBank, a knowledge bank of 155k situational norms. This re...

The ethical ambiguity of AI data enrichment: Measuring gaps in research ethics norms and practices

The technical progression of artificial intelligence (AI) research has b...

A Defeasible Calculus for Zetetic Agents

The study of defeasible reasoning unites epistemologists with those work...