Author

We introduce generative interpretation, a new approach to estimating contractual
meaning using large language models. As AI triumphalism is the order of the day,
we proceed by way of grounded case studies, each illustrating the capabilities of these
novel tools in distinct ways. Taking well-known contracts opinions, and sourcing the
actual agreements that they adjudicated, we show that AI models can help factfinders
ascertain ordinary meaning in context, quantify ambiguity, and fill gaps in parties’
agreements. We 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, we
consider their implications for judicial practice and contract theory. Using large
language models permits courts to estimate what the parties intended cheaply and
accurately, and as such generative interpretation unsettles the current interpretative
stalemate. Their use responds to 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, we argue it can become
the new workhorse of contractual interpretation.

I hypothesize that different experiences with online contracting have led some consumers to see contracts—both online and offline—in distinctive ways. Experimenting on a large, nationally representative sample, this paper provides evidence of age-based and experience-based differences in views of consumer contract formation and breach. I show that younger subjects who have entered into more online contracts are likelier than older ones to think that contracts can be formed online, that digital contracts are legitimate while oral contracts are not, and that contract law is unforgiving of breach.

I argue that such individual differences in views of contract formation and enforceability might lead firms to discriminate among consumers. There is some evidence that businesses are already using variance in views of contract to induce consumers to purchase goods they would not otherwise have. I conclude by suggesting how the law might respond to such behavior.