# Learning Norms via Natural Language Teachings

arXiv: https://arxiv.org/abs/2201.10556 · HTML: https://mlsanity.com/paper/2201.10556/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 40 references that are in the map.
- First posted on arXiv 20 Jan 2022.

## Builds on (most cited first, 1 of 1)

- [Towards a General-Purpose Belief Maintenance System](https://mlsanity.com/paper/1304.3084/) (2013)

## Built on by (most cited first, 4 of 4)

- [A Defeasible Deontic Calculus for Resolving Norm Conflicts](https://mlsanity.com/paper/2407.04869/) (2024)
- [Reasoning and Planning with Dynamically Changing Norms](https://mlsanity.com/paper/2605.27622/) (2026)
- [Interactively Diagnosing Errors in a Semantic Parser](https://mlsanity.com/paper/2407.06400/) (2024)
- [Knowledge Management in the Companion Cognitive Architecture](https://mlsanity.com/paper/2407.06401/) (2024)

## Abstract (arXiv)

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.