mlsanityData to 14 Oct 2026

Fairness: from the ethical principle to the practice of Machine Learning development as an ongoing agreement with stakeholders

arXiv 2304.06031 ↗First posted 22 Mar 2023cs.CY cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper clarifies why bias cannot be completely mitigated in Machine Learning (ML) and proposes an end-to-end methodology to translate the ethical principle of justice and fairness into the practice of ML development as an ongoing agreement with stakeholders. The pro-ethical iterative process presented in the paper aims to challenge asymmetric power dynamics in the fairness decision making within ML design and support ML development teams to identify, mitigate and monitor bias at each step of ML systems development. The process also provides guidance on how to explain the always imperfect trade-offs in terms of bias to users.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 114 references that are in the map. First posted on arXiv 22 Mar 2023.

Builds on

28 of 114 references.

References · 28

  1. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  2. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,312
  3. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 956
  4. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 924
  5. 2016Semantics derived automatically from language corpora contain human-like biasescited by 901
  6. 2020It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learnerscited by 669
  7. 2016Inherent Trade-Offs in the Fair Determination of Risk Scorescited by 586
  8. 2019Release Strategies and the Social Impacts of Language Modelscited by 513
  9. 2020Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditingcited by 384
  10. 2019Social Bias Frames: Reasoning about Social and Power Implications of Languagecited by 380
  11. 2017Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypescited by 253
  12. 2019A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cyclecited by 193
16 more
  1. 2019Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddingscited by 147
  2. 2022Power to the People? Opportunities and Challenges for Participatory AIcited by 138
  3. 2019The Ethics of AI Ethics -- An Evaluation of Guidelinescited by 129
  4. 2020Participation is not a Design Fix for Machine Learningcited by 111
  5. 2019The role of artificial intelligence in achieving the Sustainable Development Goalscited by 100
  6. 2020Why Fairness Cannot Be Automated: Bridging the Gap Between EU Non-Discrimination Law and AIcited by 81
  7. 2021Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions?cited by 46
  8. 2021The Challenge of Value Alignment: from Fairer Algorithms to AI Safetycited by 35
  9. 2020Participatory Problem Formulation for Fairer Machine Learning Through Community Based System Dynamicscited by 31
  10. 2021Ethics as a service: a pragmatic operationalisation of AI Ethicscited by 19
  11. 2021The Limits of Global Inclusion in AI Developmentcited by 14
  12. 2021Why and How Governments Should Monitor AI Developmentcited by 14
  13. 2018A Broader View on Bias in Automated Decision-Making: Reflecting on Epistemology and Dynamicscited by 10
  14. 2018Linking Artificial Intelligence Principlescited by 8
  15. 2021Actionable Principles for Artificial Intelligence Policy: Three Pathwayscited by 5
  16. 2020Implementing AI Ethics in Practice: An Empirical Evaluation of the RESOLVEDD Strategycited by 3

Built on by

Not cited yet.