mlsanityData to 7 Oct 2026

A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle

arXiv 1901.10002 ↗First posted 28 Jan 2019cs.LG stat.MLcited by 192

Not on the map. Why?

Abstract (arXiv)

As machine learning (ML) increasingly affects people and society, awareness of its potential unwanted consequences has also grown. To anticipate, prevent, and mitigate undesirable downstream consequences, it is critical that we understand when and how harm might be introduced throughout the ML life cycle. In this paper, we provide a framework that identifies seven distinct potential sources of downstream harm in machine learning, spanning data collection, development, and deployment. In doing so, we aim to facilitate more productive and precise communication around these issues, as well as more direct, application-grounded ways to mitigate them.

Key facts. Cited by 192 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 31; 2023: 41; 2024: 52; 2025: 35; 2026: 30.

192 papers.

Sort:

By area:

  1. 2024GPT-4o System Cardcited by 4,467
  2. 2023Bias and Fairness in Large Language Models: A Surveycited by 626
  3. 2024Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agentscited by 63
  4. 2021Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translationcited by 62
  5. 2023Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulationcited by 60
  6. 2024Beyond prompt brittleness: Evaluating the reliability and consistency of political worldviews in LLMscited by 55
  7. 2024Fairness Feedback Loops: Training on Synthetic Data Amplifies Biascited by 55
  8. 2023Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimescited by 52
  9. 2022Representation Bias in Data: A Survey on Identification and Resolution Techniquescited by 37
  10. 2022A Validity Perspective on Evaluating the Justified Use of Data-driven Decision-making Algorithmscited by 30
  11. 2024Farsight: Fostering Responsible AI Awareness During AI Application Prototypingcited by 28
  12. 2022From plane crashes to algorithmic harm: applicability of safety engineering frameworks for responsible MLcited by 26
38 more
  1. 2023On the application of Large Language Models for language teaching and assessment technologycited by 26
  2. 2024Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Surveycited by 23
  3. 2022Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Surveycited by 22
  4. 2022Men Also Do Laundry: Multi-Attribute Bias Amplificationcited by 21
  5. 2024LLM-Driven Robots Risk Enacting Discrimination, Violence, and Unlawful Actionscited by 21
  6. 2022Bias in Automated Speaker Recognitioncited by 20
  7. 2023Bias and Fairness in Chatbots: An Overviewcited by 20
  8. 2023Smiling Women Pitching Down: Auditing Representational and Presentational Gender Biases in Image Generative AIcited by 19
  9. 2023Better, Not Just More: Data-Centric Machine Learning for Earth Observationcited by 19
  10. 2024SCoFT: Self-Contrastive Fine-Tuning for Equitable Image Generationcited by 19
  11. 2025Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs)cited by 19
  12. 2022The worst of both worlds: A comparative analysis of errors in learning from data in psychology and machine learningcited by 17
  13. 2023Ethical Considerations for Responsible Data Curationcited by 17
  14. 2024Beyond Behaviorist Representational Harms: A Plan for Measurement and Mitigationcited by 17
  15. 2024Beyond Binary Gender Labels: Revealing Gender Biases in LLMs through Gender-Neutral Name Predictionscited by 17
  16. 2024BendVLM: Test-Time Debiasing of Vision-Language Embeddingscited by 17
  17. 2023Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoMLcited by 16
  18. 2022Robots Enact Malignant Stereotypescited by 14
  19. 2024Verifiable evaluations of machine learning models using zkSNARKscited by 14
  20. 2023Scaling Laws Do Not Scalecited by 13
  21. 2024The METRIC-framework for assessing data quality for trustworthy AI in medicine: a systematic reviewcited by 13
  22. 2024The Pursuit of Fairness in Artificial Intelligence Models: A Surveycited by 13
  23. 2022How Gender Debiasing Affects Internal Model Representations, and Why It Matterscited by 12
  24. 2022A Sandbox Tool to Bias(Stress)-Test Fairness Algorithmscited by 12
  25. 2022Towards a multi-stakeholder value-based assessment framework for algorithmic systemscited by 12
  26. 2022VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectivescited by 12
  27. 2023Metrics for Dataset Demographic Bias: A Case Study on Facial Expression Recognitioncited by 12
  28. 2023A Classification of Feedback Loops and Their Relation to Biases in Automated Decision-Making Systemscited by 12
  29. 2024A Unified Framework and Dataset for Assessing Societal Bias in Vision-Language Modelscited by 11
  30. 2024Blind Spots and Biases: Exploring the Role of Annotator Cognitive Biases in NLPcited by 11
  31. 2022Fairness and Bias in Robot Learningcited by 10
  32. 2021SoK: Machine Learning Governancecited by 9
  33. 2022Assessing Demographic Bias Transfer from Dataset to Model: A Case Study in Facial Expression Recognitioncited by 9
  34. 2023Racial Bias within Face Recognition: A Surveycited by 9
  35. 2024DF-DM: A foundational process model for multimodal data fusion in the artificial intelligence eracited by 9
  36. 2024Certifying Counterfactual Bias in LLMscited by 9
  37. 2024The Impact of Inference Acceleration on Bias of LLMscited by 9
  38. 2022Towards an Enhanced Understanding of Bias in Pre-trained Neural Language Models: A Survey with Special Emphasis on Affective Biascited by 8

50 most cited of 192 All 192 (JSON)