# Beneficent Intelligence: A Capability Approach to Modeling Benefit, Assistance, and Associated Moral Failures through AI Systems

arXiv: https://arxiv.org/abs/2308.00868 · HTML: https://mlsanity.com/paper/2308.00868/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 96 references that are in the map.
- First posted on arXiv 1 Aug 2023.

## Builds on (most cited first, 9 of 9)

- [The Values Encoded in Machine Learning Research](https://mlsanity.com/paper/2106.15590/) (2021)
- [The Fallacy of AI Functionality](https://mlsanity.com/paper/2206.09511/) (2022)
- [Problem Formulation and Fairness](https://mlsanity.com/paper/1901.02547/) (2019)
- [Envisioning Communities: A Participatory Approach Towards AI for Social Good](https://mlsanity.com/paper/2105.01774/) (2021)
- [A Validity Perspective on Evaluating the Justified Use of Data-driven Decision-making Algorithms](https://mlsanity.com/paper/2206.14983/) (2022)
- [Dark Patterns at Scale: Findings from a Crawl of 11K Shopping Websites](https://mlsanity.com/paper/1907.07032/) (2019)
- [What Makes a Dark Pattern... Dark? Design Attributes, Normative Considerations, and Measurement Methods](https://mlsanity.com/paper/2101.04843/) (2021)
- [Four Years of FAccT: A Reflexive, Mixed-Methods Analysis of Research Contributions, Shortcomings, and Future Prospects](https://mlsanity.com/paper/2206.06738/) (2022)
- [Whose Side are Ethics Codes On? Power, Responsibility and the Social Good](https://mlsanity.com/paper/2002.01559/) (2020)

## Built on by (most cited first, 9 of 9)

- [Beyond Preferences in AI Alignment](https://mlsanity.com/paper/2408.16984/) (2024)
- [A Robot Walks into a Bar: Can Language Models Serve as Creativity Support Tools for Comedy? An Evaluation of LLMs' Humour Alignment with Comedians](https://mlsanity.com/paper/2405.20956/) (2024)
- [Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value](https://mlsanity.com/paper/2512.03399/) (2025)
- [Kantian Deontology Meets AI Alignment: Towards Morally Grounded Fairness Metrics](https://mlsanity.com/paper/2311.05227/) (2023)
- [A Capability Approach to AI Ethics](https://mlsanity.com/paper/2502.03469/) (2025)
- [Model-Based Soft Maximization of Suitable Metrics of Long-Term Human Power](https://mlsanity.com/paper/2508.00159/) (2025)
- [Three Kinds of AI Ethics](https://mlsanity.com/paper/2503.18842/) (2025)
- [The Illusion of Opting in AI-Mediated Consequential Decisions](https://mlsanity.com/paper/2605.28210/) (2026)
- [A Fair Objective for Human-Empowerment-Preserving AI: Desiderata, Design, and Likely Behavioral Consequences](https://mlsanity.com/paper/2608.08240/) (2026)

## Abstract (arXiv)

The prevailing discourse around AI ethics lacks the language and formalism necessary to capture the diverse ethical concerns that emerge when AI systems interact with individuals. Drawing on Sen and Nussbaum's capability approach, we present a framework formalizing a network of ethical concepts and entitlements necessary for AI systems to confer meaningful benefit or assistance to stakeholders. Such systems enhance stakeholders' ability to advance their life plans and well-being while upholding their fundamental rights. We characterize two necessary conditions for morally permissible interactions between AI systems and those impacted by their functioning, and two sufficient conditions for realizing the ideal of meaningful benefit. We then contrast this ideal with several salient failure modes, namely, forms of social interactions that constitute unjustified paternalism, coercion, deception, exploitation and domination. The proliferation of incidents involving AI in high-stakes domains underscores the gravity of these issues and the imperative to take an ethics-led approach to AI systems from their inception.