
2 minute read
Yonathan A. Arbel
Generative Interpretation
N.Y.U. Law Review (forthcoming 2024) (with David A. Hoffman).
Artificial intelligence (AI) has shown great promise in a variety of applications. But does AI have anything to add to the judicial craft? In his recent work, co-authored with Professor Dave Hoffman (University of Pennsylvania, Carey School of Law), Arbel explores this question.
They introduce generative interpretation, a new approach to estimating contractual meaning using AI large language models. By taking wellknown contracts opinions, and after sourcing the actual agreements that they adjudicated, they show that AI models can help factfinders ascertain ordinary meaning in context, quantify ambiguity, and fill gaps in parties’ agreements. They also illustrate how models can calculate the probative value of individual pieces of extrinsic evidence.
After offering best practices for the use of these models given their limitations, they consider the implications of using AI models for judicial practice and contract theory. The use of these models allows courts to estimate what the parties intended cheaply and accurately; as such, generative interpretation unsettles the current interpretative stalemate. Their use responds to both efficiency-minded textualists and justice-oriented contextualists, who argue about whether parties will prefer cost and certainty or accuracy and fairness. Parties—and courts—would prefer a middle path, in which adjudicators strive to predict what the contract really meant, admitting just enough context to approximate reality while avoiding unguided and biased assimilation of evidence. As generative interpretation offers this possibility, the authors argue that it can become the new workhorse of contractual interpretation.