Value-Based Rationales Improve Social Experience: A Multiagent Simulation Study
Not on the map. Why?
Abstract (arXiv)
We propose Exanna, a framework to realize agents that incorporate values in decision making. An Exannaagent considers the values of itself and others when providing rationales for its actions and evaluating the rationales provided by others. Via multiagent simulation, we demonstrate that considering values in decision making and producing rationales, especially for norm-deviating actions, leads to (1) higher conflict resolution, (2) better social experience, (3) higher privacy, and (4) higher flexibility.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 7 of its 50 references that are in the map. First posted on arXiv 4 Aug 2024.
Builds on
7 of 50 references.
References · 7
- 2018TED: Teaching AI to Explain its Decisionscited by 33
- 2021Probabilistic Sufficient Explanationscited by 24
- 2023A computational framework for human valuescited by 10
- 2022Macro Ethics Principles for Responsible AI Systems: Taxonomy and Future Directionscited by 7
- 2024Norm Enforcement with a Soft Touch: Faster Emergence, Happier Agentscited by 4
- 2022Socially Intelligent Genetic Agents for the Emergence of Explicit Normscited by 3
- 2023PACCART: Reinforcing Trust in Multiuser Privacy Agreement Systemscited by 2
Built on by
Citing papers per year: 2025: 1.
1 paper.