mlsanityData to 7 Oct 2026

Deceptive Alignment Monitoring

arXiv 2307.10569 ↗First posted 20 Jul 2023cs.LG cs.AIcited by 12

Not on the map. Why?

Abstract (arXiv)

As the capabilities of large machine learning models continue to grow, and as the autonomy afforded to such models continues to expand, the spectre of a new adversary looms: the models themselves. The threat that a model might behave in a seemingly reasonable manner, while secretly and subtly modifying its behavior for ulterior reasons is often referred to as deceptive alignment in the AI Safety & Alignment communities. Consequently, we call this new direction Deceptive Alignment Monitoring. In this work, we identify emerging directions in diverse machine learning subfields that we believe will become increasingly important and intertwined in the near future for deceptive alignment monitoring, and we argue that advances in these fields present both long-term challenges and new research opportunities. We conclude by advocating for greater involvement by the adversarial machine learning community in these emerging directions.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 26 of its 30 references that are in the map. First posted on arXiv 20 Jul 2023.

Builds on

26 of 30 references.

References · 26

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  3. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  4. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  5. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  6. 2022Emergent Abilities of Large Language Modelscited by 2,483
  7. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,116
  8. 2022Mass-Editing Memory in a Transformercited by 976
  9. 2023Instruction Tuning with GPT-4cited by 676
  10. 2023Are Emergent Abilities of Large Language Models a Mirage?cited by 515
  11. 2022Memory-Based Model Editing at Scalecited by 443
  12. 2023Aligning Text-to-Image Models using Human Feedbackcited by 418
14 more
  1. 2023DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretrainingcited by 385
  2. 2023Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervisioncited by 318
  3. 2023SemDeDup: Data-efficient learning at web-scale through semantic deduplicationcited by 295
  4. 2021Unsolved Problems in ML Safetycited by 291
  5. 2023Poisoning Web-Scale Training Datasets is Practicalcited by 276
  6. 2022Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptorscited by 267
  7. 2019Risks from Learned Optimization in Advanced Machine Learning Systemscited by 250
  8. 2022The Alignment Problem from a Deep Learning Perspectivecited by 246
  9. 2023Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmarkcited by 174
  10. 2023RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputscited by 104
  11. 2023Detecting Edit Failures In Large Language Models: An Improved Specificity Benchmarkcited by 62
  12. 2022A Modern Self-Referential Weight Matrix That Learns to Modify Itselfcited by 40
  13. 2023Internet Explorer: Targeted Representation Learning on the Open Webcited by 21
  14. 2022Eliminating Meta Optimization Through Self-Referential Meta Learningcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 6; 2026: 2.

12 papers.

  1. 2023Large Language Model Alignment: A Surveycited by 241
  2. 2023Deception Abilities Emerged in Large Language Modelscited by 99
  3. 2024Personality Alignment of Large Language Modelscited by 36
  4. 2025Adversarial Attacks on Robotic Vision Language Action Modelscited by 31
  5. 2024AI Risk Management Should Incorporate Both Safety and Securitycited by 17
  6. 2025Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergiescited by 2
  7. 2025Against racing to AGI: Cooperation, deterrence, and catastrophic riskscited by 2
  8. 2025Research Superalignment Should Advance Now with Alternating Competence and Conformity Optimizationcited by 1
  9. 2026Mitigating loss of control in advanced AI systems through instrumental goal trajectoriescited by 1
  10. 2025Towards Integrated Alignmentcited by 0
  11. 2025An Aristotelian ontology of instrumental goals: Structural features to be managed and not failures to be eliminatedcited by 0
  12. 2026A three-dimensional typology of agency for advanced AI systemscited by 0