Value Alignment

Value Alignment is a framework in the ethics of automated decision-making that specifies how artificial systems should be designed to adopt and act in accordance with human values and moral principles.

106

Publications

5.8K

Citations

354

Authors

163

Institutions

Publications per year

2017–2026

79

Authors

354

  1. AL
    Augustin Landier

    HEC Paris, France

    4 publications · 145 citations

    4

    h-index

  2. DH
    Dylan Hadfield-Menell

    University of California, Berkeley, United States

    4 publications · 506 citations

    4

    h-index

  3. AD
    Anca D. Dragan

    University of California, Berkeley, United States

    3 publications · 482 citations

    3

    h-index

  4. PM
    Patrícia Macedo

    Instituto Politecnico de Setubal, Portugal

    3 publications · 73 citations

    3

    h-index

  5. PS
    Parinitha Sastry

    Toulouse School of Economics, France

    3 publications · 105 citations

    3

    h-index

1–5 of 354

Venues

  1. arXiv (Cornell University)

    Repository · 12 publications · 759 citations

    11

    h-index

  2. SSRN Electronic Journal

    Repository · 5 publications · 166 citations

    5

    h-index

  3. Ethics and Information Technology

    3 publications · 81 citations

    3

    h-index

  4. Journal of Artificial Intelligence Research

    JAIR · 2 publications · 69 citations

    2

    h-index

  5. Computer

    2 publications · 239 citations

    2

    h-index

1–5