# AI Alignment Dialogues: An Interactive Approach to AI Alignment in Support Agents

arXiv: https://arxiv.org/abs/2301.06421 · HTML: https://mlsanity.com/paper/2301.06421/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 68 references that are in the map.
- First posted on arXiv 16 Jan 2023.

## Builds on (most cited first, 7 of 7)

- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [Cooperative Inverse Reinforcement Learning](https://mlsanity.com/paper/1606.03137/) (2016)
- [Research Priorities for Robust and Beneficial Artificial Intelligence](https://mlsanity.com/paper/1602.03506/) (2016)
- [Occam's razor is insufficient to infer the preferences of irrational agents](https://mlsanity.com/paper/1712.05812/) (2017)
- [Inverse Reinforcement Learning with Simultaneous Estimation of Rewards and Dynamics](https://mlsanity.com/paper/1604.03912/) (2016)
- [Responsible Autonomy](https://mlsanity.com/paper/1706.02513/) (2017)
- [Towards Understanding Emotional Intelligence for Behavior Change Chatbots](https://mlsanity.com/paper/1907.10664/) (2019)

## Built on by (most cited first, 1 of 1)

- [PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2308.02585/) (2023)

## Abstract (arXiv)

AI alignment is about ensuring AI systems only pursue goals and activities that are beneficial to humans. Most of the current approach to AI alignment is to learn what humans value from their behavioural data. This paper proposes a different way of looking at the notion of alignment, namely by introducing AI Alignment Dialogues: dialogues with which users and agents try to achieve and maintain alignment via interaction. We argue that alignment dialogues have a number of advantages in comparison to data-driven approaches, especially for behaviour support agents, which aim to support users in achieving their desired future behaviours rather than their current behaviours. The advantages of alignment dialogues include allowing the users to directly convey higher-level concepts to the agent, and making the agent more transparent and trustworthy. In this paper we outline the concept and high-level structure of alignment dialogues. Moreover, we conducted a qualitative focus group user study from which we developed a model that describes how alignment dialogues affect users, and created design suggestions for AI alignment dialogues. Through this we establish foundations for AI alignment dialogues and shed light on what requires further development and research.