# Building Ethically Bounded AI

arXiv: https://arxiv.org/abs/1812.03980 · HTML: https://mlsanity.com/paper/1812.03980/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Dec 2018.

## Built on by (most cited first, 22 of 22)

- [Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directions](https://mlsanity.com/paper/2510.25445/) (2025)
- [Thinking Fast and Slow in AI: the Role of Metacognition](https://mlsanity.com/paper/2110.01834/) (2021)
- [Making Human-Like Trade-offs in Constrained Environments by Learning from Demonstrations](https://mlsanity.com/paper/2109.11018/) (2021)
- [Combining Fast and Slow Thinking for Human-like and Efficient Navigation in Constrained Environments](https://mlsanity.com/paper/2201.07050/) (2022)
- [When Is It Acceptable to Break the Rules? Knowledge Representation of Moral Judgement Based on Empirical Data](https://mlsanity.com/paper/2201.07763/) (2022)
- [Minimum Levels of Interpretability for Artificial Moral Agents](https://mlsanity.com/paper/2307.00660/) (2023)
- [Ethical AI: Towards Defining a Collective Evaluation Framework](https://mlsanity.com/paper/2506.00233/) (2025)
- [Learning Behavioral Soft Constraints from Demonstrations](https://mlsanity.com/paper/2202.10407/) (2022)
- [Constraint-Guided Reinforcement Learning: Augmenting the Agent-Environment-Interaction](https://mlsanity.com/paper/2104.11918/) (2021)
- [Measuring Ethics in AI with AI: A Methodology and Dataset Construction](https://mlsanity.com/paper/2107.11913/) (2021)
- [Computational-level Analysis of Constraint Compliance for General Intelligence](https://mlsanity.com/paper/2303.04352/) (2023)
- [Value-based Fast and Slow AI Nudging](https://mlsanity.com/paper/2307.07628/) (2023)
- [ValuePilot: A Two-Phase Framework for Value-Driven Decision-Making](https://mlsanity.com/paper/2503.04569/) (2025)
- [An AGM Approach to Revising Preferences](https://mlsanity.com/paper/2112.14243/) (2021)
- [Logic-Based Ethical Planning](https://mlsanity.com/paper/2206.00595/) (2022)
- [Toward Constraint Compliant Goal Formulation and Planning](https://mlsanity.com/paper/2405.12862/) (2024)
- [AI Ethics and Social Norms: Exploring ChatGPT's Capabilities From What to How](https://mlsanity.com/paper/2504.18044/) (2025)
- [HAVA: Hybrid Approach to Value-Alignment through Reward Weighing for Reinforcement Learning](https://mlsanity.com/paper/2505.15011/) (2025)
- [A cybersecurity AI agent selection and decision support framework](https://mlsanity.com/paper/2510.01751/) (2025)
- [The Algebra of Meaning: Why Machines Need Montague More Than Moore's Law](https://mlsanity.com/paper/2510.06559/) (2025)
- [Toward Virtuous Reinforcement Learning: A Critique and Roadmap](https://mlsanity.com/paper/2512.04246/) (2025)
- [ValuePilot: A Two-Phase Framework for Value-Driven Decision-Making](https://mlsanity.com/paper/2512.13716/) (2025)

## Abstract (arXiv)

The more AI agents are deployed in scenarios with possibly unexpected situations, the more they need to be flexible, adaptive, and creative in achieving the goal we have given them. Thus, a certain level of freedom to choose the best path to the goal is inherent in making AI robust and flexible enough. At the same time, however, the pervasive deployment of AI in our life, whether AI is autonomous or collaborating with humans, raises several ethical challenges. AI agents should be aware and follow appropriate ethical principles and should thus exhibit properties such as fairness or other virtues. These ethical principles should define the boundaries of AI's freedom and creativity. However, it is still a challenge to understand how to specify and reason with ethical boundaries in AI agents and how to combine them appropriately with subjective preferences and goal specifications. Some initial attempts employ either a data-driven example-based approach for both, or a symbolic rule-based approach for both. We envision a modular approach where any AI technique can be used for any of these essential ingredients in decision making or decision support systems, paired with a contextual approach to define their combination and relative weight. In a world where neither humans nor AI systems work in isolation, but are tightly interconnected, e.g., the Internet of Things, we also envision a compositional approach to building ethically bounded AI, where the ethical properties of each component can be fruitfully exploited to derive those of the overall system. In this paper we define and motivate the notion of ethically-bounded AI, we describe two concrete examples, and we outline some outstanding challenges.