mlsanityData to 7 Oct 2026

Concrete Problems in AI Safety, Revisited

arXiv 2401.10899 ↗First posted 18 Dec 2023cs.CY cs.AIcited by 21

Not on the map. Why?

Abstract (arXiv)

As AI systems proliferate in society, the AI community is increasingly preoccupied with the concept of AI Safety, namely the prevention of failures due to accidents that arise from an unanticipated departure of a system's behavior from designer intent in AI deployment. We demonstrate through an analysis of real world cases of such incidents that although current vocabulary captures a range of the encountered issues of AI deployment, an expanded socio-technical framing will be required for a more complete understanding of how AI systems and implemented safety mechanisms fail and succeed in real life.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 9 of its 34 references that are in the map. First posted on arXiv 18 Dec 2023.

Builds on

9 of 34 references.

References · 9

  1. 2016Concrete Problems in AI Safetycited by 1,582
  2. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,242
  3. 2019On Evaluating Adversarial Robustnesscited by 442
  4. 2019Show Your Work: Improved Reporting of Experimental Resultscited by 164
  5. 2017A General Safety Framework for Learning-Based Control in Uncertain Robotic Systemscited by 150
  6. 2017AI Safety Gridworldscited by 108
  7. 2020Saving Face: Investigating the Ethical Concerns of Facial Recognition Auditingcited by 89
  8. 2016Engineering Safety in Machine Learningcited by 24
  9. 2020Robot Rights? Let's Talk about Human Welfare Insteadcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 6; 2026: 9.

21 papers.

Sort:

By area:

  1. 2024LLM-based NLG Evaluation: Current Status and Challengescited by 71
  2. 2025Toward an Evaluation Science for Generative AI Systemscited by 42
  3. 2024Preference Tuning For Toxicity Mitigation Generalizes Across Languagescited by 31
  4. 2025Reality Check: A New Evaluation Ecosystem Is Necessary to Understand AI's Real World Effectscited by 18
  5. 2024AI Risk Management Should Incorporate Both Safety and Securitycited by 17
  6. 2024The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resourcescited by 11
  7. 2025Whose View of Safety? A Deep DIVE Dataset for Pluralistic Alignment of Text-to-Image Modelscited by 11
  8. 2024AI Alignment through Reinforcement Learning from Human Feedback? Contradictions and Limitationscited by 10
  9. 2025AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Securitycited by 9
  10. 2024Aligning Large Language Models from Self-Reference AI Feedback with one General Principlecited by 2
  11. 2025MCP-AI: Protocol-Driven Intelligence Framework for Autonomous Reasoning in Healthcarecited by 1
  12. 2026Risk-Calibrated Learning: Minimizing Fatal Errors in Medical AIcited by 1
9 more
  1. 2025Preliminary Quantitative Study on Explainability and Trust in AI Systemscited by 0
  2. 2026Relative Principals, Pluralistic Alignment, and the Structural Value Alignment Problemcited by 0
  3. 2026Improving Model Safety by Targeted Error Correctioncited by 0
  4. 2026StepGuard: Guarding Web Navigation via Single-Step Calibrationcited by 0
  5. 2026Unsafe at any AUC: Unlearned Lessons from Sociotechnical Disasters for Responsible AIcited by 0
  6. 2026Toward a Theory of Value in AI Alignmentcited by 0
  7. 2026Co-constructing sociotechnical AI governance: participatory system mapping using algorithm registerscited by 0
  8. 2026Collective Loss of Control in LLM Agent Systems: An Epidemic Account of Mutation, Contagion, and Recoverycited by 0
  9. 2026The Ethics of Artificial Intelligence in Military Operationscited by 0