# Taking Principles Seriously: A Hybrid Approach to Value Alignment

arXiv: https://arxiv.org/abs/2012.11705 · HTML: https://mlsanity.com/paper/2012.11705/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Dec 2020.

## Built on by (most cited first, 13 of 13)

- [Hybrid Approaches for Moral Value Alignment in AI Agents: a Manifesto](https://mlsanity.com/paper/2312.01818/) (2023)
- [Value Preferences Estimation and Disambiguation in Hybrid Participatory Systems](https://mlsanity.com/paper/2402.16751/) (2024)
- [AI, Opacity, and Personal Autonomy](https://mlsanity.com/paper/2210.08995/) (2022)
- [Liability regimes in the age of AI: a use-case driven analysis of the burden of proof](https://mlsanity.com/paper/2211.01817/) (2022)
- [Fairness through Social Welfare Optimization](https://mlsanity.com/paper/2102.00311/) (2021)
- [When is it permissible for artificial intelligence to lie? A trust-based approach](https://mlsanity.com/paper/2103.05434/) (2021)
- [Justifications for Democratizing AI Alignment and Their Prospects](https://mlsanity.com/paper/2507.19548/) (2025)
- [Operationalising Rawlsian Ethics for Fairness in Norm-Learning Agents](https://mlsanity.com/paper/2412.15163/) (2024)
- [Evaluating Human-LLM Representation Alignment: A Case Study on Affective Sentence Generation for Augmentative and Alternative Communication](https://mlsanity.com/paper/2503.11881/) (2025)
- [Contemplative Artificial Intelligence](https://mlsanity.com/paper/2504.15125/) (2025)
- [Who Owns The Robot?: Four Ethical and Socio-technical Questions about Wellbeing Robots in the Real World through Community Engagement](https://mlsanity.com/paper/2509.02624/) (2025)
- [The Alignment Target Problem: Divergent Moral Judgments of Humans, AI Systems, and Their Designers](https://mlsanity.com/paper/2604.24155/) (2026)
- [Logic, Optimization, and Artificial Intelligence](https://mlsanity.com/paper/2607.15532/) (2026)

## Abstract (arXiv)

An important step in the development of value alignment (VA) systems in AI is understanding how VA can reflect valid ethical principles. We propose that designers of VA systems incorporate ethics by utilizing a hybrid approach in which both ethical reasoning and empirical observation play a role. This, we argue, avoids committing the "naturalistic fallacy," which is an attempt to derive "ought" from "is," and it provides a more adequate form of ethical reasoning when the fallacy is not committed. Using quantified model logic, we precisely formulate principles derived from deontological ethics and show how they imply particular "test propositions" for any given action plan in an AI rule base. The action plan is ethical only if the test proposition is empirically true, a judgment that is made on the basis of empirical VA. This permits empirical VA to integrate seamlessly with independently justified ethical principles.