CoChat
Sign Up
Cited by 52Ethics and Social Impacts of AIPhilosophical Ethics and TheoryInnovation, Sustainability, Human-Machine Systems

The DOI matches its Crossref record; 54 of the 54 references it cites were found in a registry or an index.

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

Gabriel, Iason, Ghazavi, Vafa·2022·Oxford Handbook of Digital Ethics
DOI 10.1093/oxfordhb/9780198857815.013.18
Open this paper in CoChat — free account

Abstract

This chapter addresses the question of how to align artificial intelligence (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 chapter, we look more closely at the question of AI 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.

Overview

Integrity signals

Registry

Crossref · 10.1093/oxfordhb/9780198857815.013.18

Cites

54 of 54 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • The ability to probe and shape LLM personality traits is pertinent to the open problem of responsible AI alignment and harm mitigation.

    “The ability to probe and shape LLM personality traits is pertinent to the open problem of responsible AI alignment54 and harm mitigation55.”

    From A psychometric framework for evaluating and shaping personality traits in large language models (2025) · cites this paper as [54]

  • Core concept and structure of MoE models lie in dynamic routing and specialization capabilities, offering promising avenues for scaling up neural networks and enhancing efficiency and adaptability in various tasks, but robustness of router must be protected against adversarial attacks.

    “The core concept and structure of MoE models lie in their dynamic routing and specialization capabilities, offering promising avenues for scaling up neural networks and enhancing their efficiency and adaptability in various tasks, but the robustness of the router must be protected against adversarial attacks [289], [298].”

    From From Google Gemini to OpenAI Q* (Q-Star): A Survey on Reshaping the Generative Artificial Intelligence (AI) Research Landscape (2025) · cites this paper as [298]

  • Recent advancements in MoE architecture have resulted in notable training cost efficiencies, especially in encoder-decoder models, with cost savings up to fivefold in certain contexts compared to dense models.

    “Recent advancements in MoE architecture have resulted in notable training cost efficiencies, especially in encoder-decoder models, with evidence showing cost savings of up to fivefold in certain contexts when compared to dense models [21], [289], [298], [287].”

    From From Google Gemini to OpenAI Q* (Q-Star): A Survey on Reshaping the Generative Artificial Intelligence (AI) Research Landscape (2025) · cites this paper as [298]

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 17

  1. 2018, Proceedings of Machine Learning Research
  2. 2018, The Measure and Mismeasure of Fairness: A Critical Review of Fair Machine Learning, arXiv,
  3. 1987, The Intentional Stance
  4. 2003, Freedom Evolves
  5. Everitt, Tom (2018), ‘Towards Safe Artificial General Intelligence’, doctoral thesis, Australian National University, https://openresearch-repository.anu.edu.au/handle/1885/164227, accessed 30 September 2021.
  6. 2017, Reinforcement Learning with Corrupted Reward Signal, International Joint Conference on Artificial Intelligence arXiv,
  7. Harari, Yuval Noah (2018) ‘Why technology favors tyranny’, The Atlantic, 322(3): 64–70.
  8. 2000, A Treatise of Human Nature
  9. 2018, AI Safety via Debate, arXiv,
  10. Artificial Intelligence: The Global Landscape of Ethics Guidelines, Nature Machine Intelligence
  11. 2016, To Predict and Serve?, Significance
  12. Ng, Andrew Y., and Stuart J. Russell (2000), ‘Algorithms for Inverse Reinforcement Learning’, ‘00 Proceedings of the Seventeenth International Conference on Machine Learning, 663–670.
  13. 1997, Equality and Priority, Ratio
  14. 2011, On What Matters
  15. 2005, Political Liberalism
  16. 1960, Some Moral and Technical Consequences of Automation, Science
  17. 2004, Coherent Extrapolated Volition

Cited by

Sorted by citations

Related

Metadata

Authors
Gabriel, I., & Ghazavi, V.
Affiliations
  • Google DeepMind (United Kingdom) (GB)
  • Harvard University (US)
ORCID
Venue
Oxford Handbook of Digital Ethics
Publisher
Oxford University Press
Published
2022-03-18
Pages
336-355
DOI
10.1093/oxfordhb/9780198857815.013.18
OpenAlex
W4221100501
Cited by
52
References
54
Citations by year
2026: 10 · 2025: 24 · 2024: 11 · 2023: 4 · 2022: 2
FWCI
36.01
Type
book chapter
Language
en
Open access
closed
Locations
Oxford University Press eBooks (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
  • Social Sciences › Arts and Humanities › Philosophy › Philosophical Ethics and Theory
  • Physical Sciences › Environmental Science › Management, Monitoring, Policy and Law › Innovation, Sustainability, Human-Machine Systems
Keywords
AI alignment, value alignment, human values, technology and values, participatory design, AI safety, AI autonomy, global values

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review