mlsanityData to 7 Oct 2026

Incomplete Contracting and AI Alignment

arXiv 1804.04268 ↗First posted 12 Apr 2018cs.AIcited by 60

Not on the map. Why?

Abstract (arXiv)

We suggest that the analysis of incomplete contracting developed by law and economics researchers can provide a useful framework for understanding the AI alignment problem and help to generate a systematic approach to finding solutions. We first provide an overview of the incomplete contracting literature and explore parallels between this work and the problem of AI alignment. As we emphasize, misalignment between principal and agent is a core focus of economic analysis. We highlight some technical results from the economics literature on incomplete contracts that may provide insights for AI alignment researchers. Our core contribution, however, is to bring to bear an insight that economists have been urged to absorb from legal scholars and other behavioral scientists: the fact that human contracting is supported by substantial amounts of external structure, such as generally available institutions (culture, law) that can supply implied terms to fill the gaps in incomplete contracts. We propose a research agenda for AI alignment work that focuses on the problem of how to build AI that can replicate the human cognitive processes that connect individual incomplete contracts with this supporting external structure.

Key facts. Cited by 60 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 4; 2023: 9; 2024: 8; 2025: 15; 2026: 18.

60 papers.

Sort:

By area:

  1. 2023Harms from Increasingly Agentic Algorithmic Systemscited by 134
  2. 2021Consequences of Misaligned AIcited by 79
  3. 2024Beyond Preferences in AI Alignmentcited by 46
  4. 2024AI Alignment with Changing and Influenceable Reward Functionscited by 33
  5. 2021What are you optimizing for? Aligning Recommender Systems with Human Valuescited by 28
  6. 2021Hard Choices in Artificial Intelligencecited by 26
  7. 2021MORAL: Aligning AI with Human Norms through Multi-Objective Reinforced Active Learningcited by 24
  8. 2022Law Informs Code: A Legal Informatics Approach to Aligning Artificial Intelligence with Humanscited by 23
  9. 2025An Economy of AI Agentscited by 17
  10. 2024LLM Theory of Mind and Alignment: Opportunities and Riskscited by 15
  11. 2023Principal-Agent Reward Shaping in MDPscited by 12
  12. 2025Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspectivecited by 12
38 more
  1. 2022Metaethical Perspectives on 'Benchmarking' AI Ethicscited by 11
  2. 2024Risks and Opportunities of Open-Source Generative AIcited by 11
  3. 2023Deep Contract Design via Discontinuous Networkscited by 10
  4. 2024On Goodhart's law, with an application to value alignmentcited by 9
  5. 2025Societal and technological progress as sewing an ever-growing, ever-changing, patchy, and polychrome quiltcited by 9
  6. 2025AI Agents and the Lawcited by 9
  7. 2023Designing Fiduciary Artificial Intelligencecited by 8
  8. 2025Societal Alignment Frameworks Can Improve LLM Alignmentcited by 8
  9. 2025Resource Rational Contractualism Should Guide AI Alignmentcited by 8
  10. 2023A Review of the Evidence for Existential Risk from AI via Misaligned Power-Seekingcited by 7
  11. 2025Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Valuecited by 6
  12. 2023Survey on AI Ethics: A Socio-technical Perspectivecited by 4
  13. 2024Improved Emotional Alignment of AI and Humans: Human Ratings of Emotions Expressed by Stable Diffusion v1, DALL-E 2, and DALL-E 3cited by 3
  14. 2021Counterfactual Planning in AGI Systemscited by 2
  15. 2025A Protocol for Trustless Verification Under Uncertaintycited by 2
  16. 2026Reward Shaping for (Inference-Time) Alignment: A Stackelberg Game Perspectivecited by 2
  17. 2026Towards Selection as Power: Bounding Decision Authority in Autonomous Agentscited by 2
  18. 2026Post-AGI Economies: Autonomy and the First Fundamental Theorem of Welfare Economicscited by 2
  19. 2022The Linguistic Blind Spot of Value-Aligned Agency, Natural and Artificialcited by 1
  20. 2023Positive AI: Key Challenges in Designing Artificial Intelligence for Wellbeingcited by 1
  21. 2024On the Undecidability of Artificial Intelligence Alignment: Machines that Haltcited by 1
  22. 2025Pricing Access to Dynamic Information Servicescited by 1
  23. 2026Multi-Agent Systems Should be Treated as Principal-Agent Problemscited by 1
  24. 2026Consequentialist Objectives and Catastrophecited by 1
  25. 2026AI Alignment via Incentives and Correctioncited by 1
  26. 2026Post-AGI Economies: Superposition and the Second Fundamental Theorem of Welfare Economicscited by 1
  27. 2026Commitment To Cooperation With Self-Negotiated Contractscited by 1
  28. 2021Demanding and Designing Aligned Cognitive Architecturescited by 0
  29. 2022Modelling the Recommender Alignment Problemcited by 0
  30. 2023Artificial Intelligence and Dual Contractcited by 0
  31. 2023Dynamic value alignment through preference aggregation of multiple objectivescited by 0
  32. 2024Systematic Characterization of the Effectiveness of Alignment in Large Language Models for Categorical Decisionscited by 0
  33. 2025AI Agents and Hard Choicescited by 0
  34. 2025On Monotonicity in AI Alignmentcited by 0
  35. 2025Getting In Contract with Large Language Models -- An Agency Theory Perspective On Large Language Model Alignmentcited by 0
  36. 2025Bridging Cultural Distance Between Models Default and Local Classroom Demands: How Global Teachers Adopt GenAI to Support Everyday Teaching Practicescited by 0
  37. 2025Corrigibility Transformation: Constructing Goals That Accept Updatescited by 0
  38. 2025Validity Is What You Needcited by 0

50 most cited of 60 All 60 (JSON)