mlsanityData to 7 Oct 2026

Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims

arXiv 2004.07213 ↗First posted 15 Apr 2020cs.CYcited by 163

Not on the map. Why?

Abstract (arXiv)

With the recent wave of progress in artificial intelligence (AI) has come a growing awareness of the large-scale impacts of AI systems, and recognition that existing regulations and norms in industry and academia are insufficient to ensure responsible AI development. In order for AI developers to earn trust from system users, customers, civil society, governments, and other stakeholders that they are building AI responsibly, they will need to make verifiable claims to which they can be held accountable. Those outside of a given organization also need effective means of scrutinizing such claims. This report suggests various steps that different stakeholders can take to improve the verifiability of claims made about AI systems and their associated development processes, with a focus on providing evidence about the safety, security, fairness, and privacy protection of AI systems. We analyze ten mechanisms for this purpose--spanning institutions, software, and hardware--and make recommendations aimed at implementing, exploring, or improving those mechanisms.

Key facts. Cited by 163 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 24; 2022: 19; 2023: 32; 2024: 31; 2025: 39; 2026: 18.

163 papers.

Sort:

By area:

  1. 2024OpenAI o1 System Cardcited by 1,220
  2. 2022Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learnedcited by 702
  3. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 364
  4. 2021Unsolved Problems in ML Safetycited by 291
  5. 2022The Alignment Problem from a Deep Learning Perspectivecited by 246
  6. 2021Trustworthy AI: From Principles to Practicescited by 206
  7. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
  8. 2023Model evaluation for extreme riskscited by 167
  9. 2023LM vs LM: Detecting Factual Errors via Cross Examinationcited by 155
  10. 2023Sociotechnical Safety Evaluation of Generative AI Systemscited by 154
  11. 2023Auditing large language models: a three-layered approachcited by 135
  12. 2023Harms from Increasingly Agentic Algorithmic Systemscited by 134
38 more
  1. 2024Black-Box Access is Insufficient for Rigorous AI Auditscited by 123
  2. 2021HIVE: Evaluating the Human Interpretability of Visual Explanationscited by 105
  3. 2023Frontier AI Regulation: Managing Emerging Risks to Public Safetycited by 95
  4. 2021Trustworthy AI: A Computational Perspectivecited by 93
  5. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 88
  6. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discoverycited by 74
  7. 2022"Help Me Help the AI": Understanding How Explainability Can Support Human-AI Interactioncited by 63
  8. 2023The Gradient of Generative AI Release: Methods and Considerationscited by 63
  9. 2024Introducing v0.5 of the AI Safety Benchmark from MLCommonscited by 60
  10. 2022Self-Destructing Models: Increasing the Costs of Harmful Dual Uses of Foundation Modelscited by 56
  11. 2021Logic Explained Networkscited by 45
  12. 20223DALL-E: Integrating Text-to-Image AI in 3D Design Workflowscited by 41
  13. 2025Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMscited by 34
  14. 2023Don't trust your eyes: on the (un)reliability of feature visualizationscited by 32
  15. 2023Open-Sourcing Highly Capable Foundation Models: An evaluation of risks, benefits, and alternative methods for pursuing open-source objectivescited by 31
  16. 2021Reviewable Automated Decision-Making: A Framework for Accountable Algorithmic Systemscited by 30
  17. 2021Outlining Traceability: A Principle for Operationalizing Accountability in Computing Systemscited by 26
  18. 2024I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Tokencited by 26
  19. 2025OpenAI's Approach to External Red Teaming for AI Models and Systemscited by 26
  20. 2021Reliability Testing for Natural Language Processing Systemscited by 25
  21. 2021Ethics-Based Auditing to Develop Trustworthy AIcited by 23
  22. 2022Towards Training Reproducible Deep Learning Modelscited by 23
  23. 2022A Hazard Analysis Framework for Code Synthesis Large Language Modelscited by 22
  24. 2023Towards Evaluating AI Systems for Moral Status Using Self-Reportscited by 21
  25. 2024The Compute Divide in Machine Learning: A Threat to Academic Contribution and Scrutiny?cited by 20
  26. 2024Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image Generationcited by 20
  27. 2021Conformity Assessments and Post-market Monitoring: A Guide to the Role of Auditing in the Proposed European AI Regulationcited by 19
  28. 2023Automated Cyber Defence: A Reviewcited by 19
  29. 2023Statistical Inference for Fairness Auditingcited by 19
  30. 2024The 2024 Foundation Model Transparency Indexcited by 18
  31. 2021Learning to run a power network with trustcited by 17
  32. 2022CLEVR-X: A Visual Reasoning Dataset for Natural Language Explanationscited by 16
  33. 2025Forecasting Rare Language Model Behaviorscited by 16
  34. 2023Protecting Society from AI Misuse: When are Restrictions on Capabilities Warranted?cited by 15
  35. 2021Explainable Machine Learning with Prior Knowledge: An Overviewcited by 14
  36. 2023A Review of the Role of Causality in Developing Trustworthy AI Systemscited by 14
  37. 2024Training Compute Thresholds: Features and Functions in AI Regulationcited by 13
  38. 2022Towards Verifiable Federated Learningcited by 11

50 most cited of 163 All 163 (JSON)