# Human Values in Multiagent Systems

arXiv: https://arxiv.org/abs/2305.02739 · HTML: https://mlsanity.com/paper/2305.02739/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 25 references that are in the map.
- First posted on arXiv 4 May 2023.

## Builds on (most cited first, 5 of 5)

- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [Trustworthy AI](https://mlsanity.com/paper/2011.02272/) (2020)
- [Acquiring Background Knowledge to Improve Moral Value Prediction](https://mlsanity.com/paper/1709.05467/) (2017)
- [Value alignment: a formal approach](https://mlsanity.com/paper/2110.09240/) (2021)
- [A Value-based Trust Assessment Model for Multi-agent Systems](https://mlsanity.com/paper/1905.13380/) (2019)

## Abstract (arXiv)

One of the major challenges we face with ethical AI today is developing computational systems whose reasoning and behaviour are provably aligned with human values. Human values, however, are notorious for being ambiguous, contradictory and ever-changing. In order to bridge this gap, and get us closer to the situation where we can formally reason about implementing values into AI, this paper presents a formal representation of values, grounded in the social sciences. We use this formal representation to articulate the key challenges for achieving value-aligned behaviour in multiagent systems (MAS) and a research roadmap for addressing them.