mlsanityData to 7 Oct 2026

The Challenge of Value Alignment: from Fairer Algorithms to AI Safety

arXiv 2101.06060 ↗First posted 15 Jan 2021cs.CYcited by 34

Not on the map. Why?

Abstract (arXiv)

This paper addresses the question of how to align AI systems with human values and situates it within a wider body of thought regarding technology and value. Far from existing in a vacuum, there has long been an interest in the ability of technology to 'lock-in' different value systems. There has also been considerable thought about how to align technologies with specific social values, including through participatory design-processes. In this paper we look more closely at the question of AI value alignment and suggest that the power and autonomy of AI systems gives rise to opportunities and challenges in the domain of value that have not been encountered before. Drawing important continuities between the work of the fairness, accountability, transparency and ethics community, and work being done by technical AI safety researchers, we suggest that more attention needs to be paid to the question of 'social value alignment' - that is, how to align AI systems with the plurality of values endorsed by groups of people, especially on the global level.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Jan 2021.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 2; 2023: 11; 2024: 8; 2025: 7; 2026: 5.

34 papers.

Sort:

By area:

  1. 2021Ethical and social risks of harm from Language Modelscited by 957
  2. 2023Towards Measuring the Representation of Subjective Global Opinions in Language Modelscited by 424
  3. 2023Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewardscited by 232
  4. 2024The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Modelscited by 136
  5. 2023Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generationcited by 128
  6. 2023Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedbackcited by 86
  7. 2023CompeteAI: Understanding the Competition Dynamics in Large Language Model-based Agentscited by 65
  8. 2022In conversation with Artificial Intelligence: aligning language models with human valuescited by 61
  9. 2024On the Essence and Prospect: An Investigation of Alignment Approaches for Big Modelscited by 21
  10. 2023From Google Gemini to OpenAI Q* (Q-Star): A Survey of Reshaping the Generative Artificial Intelligence (AI) Research Landscapecited by 18
  11. 2022Warmth and competence in human-agent cooperationcited by 11
  12. 2025The Lock-in Hypothesis: Stagnation by Algorithmcited by 11
22 more
  1. 2024How Are LLMs Mitigating Stereotyping Harms? Learning from Search Engine Studiescited by 9
  2. 2023A Critical Examination of the Ethics of AI-Mediated Peer Reviewcited by 8
  3. 2023How should the advent of large language models affect the practice of science?cited by 8
  4. 2025LIVS: A Pluralistic Alignment Dataset for Inclusive Public Spacescited by 8
  5. 2024Legal Minds, Algorithmic Decisions: How LLMs Apply Constitutional Principles in Complex Scenarioscited by 7
  6. 2024Sociotechnical Implications of Generative Artificial Intelligence for Information Accesscited by 6
  7. 2024Strong Preferences Affect the Robustness of Preference Models and Value Alignmentcited by 4
  8. 2025Hiding in the AI Traffic: Abusing MCP for LLM-Powered Agentic Red Teamingcited by 4
  9. 2025Maximizing Signal in Human-Model Preference Alignmentcited by 2
  10. 2026Structuring the Space of Sociotechnical Alignmentcited by 2
  11. 2023The Chai Platform's AI Safety Frameworkcited by 1
  12. 2023Steps Towards Satisficing Distributed Dynamic Team Trustcited by 1
  13. 2024On the Undecidability of Artificial Intelligence Alignment: Machines that Haltcited by 1
  14. 2024Measuring Error Alignment for Decision-Making Systemscited by 1
  15. 2025Beyond Algorethics: Addressing the Ethical and Anthropological Challenges of AI Recommender Systemscited by 1
  16. 2026Mitigating loss of control in advanced AI systems through instrumental goal trajectoriescited by 1
  17. 2023Fairness: from the ethical principle to the practice of Machine Learning development as an ongoing agreement with stakeholderscited by 0
  18. 2025The Value of Gen-AI Conversations: A bottom-up Framework for AI Value Alignmentcited by 0
  19. 2025An Aristotelian ontology of instrumental goals: Structural features to be managed and not failures to be eliminatedcited by 0
  20. 2026PLOT: Enhancing Preference Learning via Optimal Transportcited by 0
  21. 2026AI Alignment From Social Choice Perspectivescited by 0
  22. 2026A Roadmap to Impactful Pluralistic Alignment Researchcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023A Multi-Level Framework for the AI Alignment Problem
  2. 2023Measuring Value Alignment
  3. 2026Toward a Theory of Value in AI Alignment
  4. 2021Value alignment: a formal approach
  5. 2024Dynamic Normativity: Necessary and Sufficient Conditions for Value Alignment
  6. 2024ValueCompass: A Framework for Measuring Contextual Value Alignment Between Human and LLMs
  7. 2026Pluralism in AI Governance: Toward Sociotechnical Alignment and Normative Coherence ↗
  8. 2026Position: Align AI to Our Aspirations, Not Our Flaws