Incomplete Contracting and AI Alignment

By Dylan Hadfield-Menell, Gillian K. Hadfield. 2018

123 citations recorded by the source corpus.

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.

Subfields: Economics and Econometrics, Management Science and Operations Research, Political Science and International Relations

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

1. Shai Shalev-Shwartz
2. Dylan Hadfield-Menell
3. David Krueger
4. Adrian Weller
5. Simon Zhuang
6. Tegan Maharaj

In Management Science and Operations Research

1. Dylan Hadfield-Menell
2. Anca Dragan
3. Umang Bhatt
4. Simon Zhuang
5. David Krueger
6. Shai Shalev-Shwartz
7. Nitarshan Rajkumar
8. Philip H. S. Torr

In Political Science and International Relations

1. Adrian Weller

Citations in the corpus

• Managing extreme AI risks amid rapid progress (2023, background): “…below), even well-meaning developers may inad-vertently create AI systems pursuing unintended goals: The reward signal used to train AI systems usually fails to fully capture the intended objectives, leading to AI systems that pursue the literal specification rather than the intended outcome 29 .”
• Consequences of Misaligned AI (2021, background): “As such, Hadfield-Menell and Hadfield note that legal and economic research should provide insight into solving misalignment (17).”
• Harms from Increasingly Agentic Algorithmic Systems (2023, methodology): “In our context, we view the principal as humans and the agent as algorithmic systems, as done in prior work [Hadfield-Menell and Hadfield 2019].”