arXiv subjects

Yonathan A. Arbel

Publications and source records attributed to Yonathan A. Arbel.

3 recordsLinked to original sources

arXiv2026

Generative Gap Filling

Most contract litigation turns on contracts that imperfectly record parties' bargains. When the parties' dispute can't be solved by interpreting the text, courts fill the gap. Scholars have long assumed that the remaining text runs out quickly, and provides thin evidence of the actual deal on the disputed point. On that view, a judge who supplies the missing term must be drawing on something else, from commercial defaults to her own policy preferences. Despite generations of work, courts have no real alternative to such unruly methods. We tested that assumption. Taking real contracts, we masked a term the parties had negotiated and asked readers to predict what we removed. Lay respondents recovered the hidden term about half the time, twice what chance predicts. Law students and lawyers did marginally better. But large language models, given nothing but the rest of the contract, recovered it nearly nine times in ten. The deal, in short, testifies to far more of the agreement than the literature assumes, including terms the parties never wrote. A contract, we argue, is like a radio signal from far away. Even when incomplete, enough of the message is carried elsewhere that the missing part can be reconstructed with the right receiver. True gaps are rarer than supposed. Courts can weigh model predictions as ordinary, contestable evidence, and parties can discipline the practice with "Choice of Model" clauses.

cs.CY↗

arXiv2026

The Generative Reasonable Person

This Article introduces the generative reasonable person, a new tool for estimating how ordinary people judge reasonableness. As claims about AI capabilities often outpace evidence, the Article proceeds empirically: adapting randomized controlled trials to large language models, it replicates three published studies of lay judgment across negligence, consent, and contract interpretation, drawing on nearly 10,000 simulated decisions. The findings reveal that models can replicate subtle patterns that run counter to textbook treatment. Like human subjects, models prioritize social conformity over cost-benefit analysis when assessing negligence, inverting the hierarchy that textbooks teach. They reproduce the paradox that material lies erode consent less than lies about a transaction's essence. And they track lay contract formalism, judging hidden fees more enforceable than fair. For two centuries, scholars have debated whether the reasonable person is empirical or normative, majoritarian or aspirational. But much of this debate assumed a constraint that no longer holds: that lay judgments are expensive to surface, slow to collect, and unavailable at scale. Generative reasonable people loosen that constraint. They offer judges empirical checks on elite intuition, give resource-constrained litigants access to simulated jury feedback, and let regulators pilot-test public comprehension, all at a fraction of survey costs. The reasonable person standard has long functioned as a vessel for judicial intuition precisely because the empirical baseline was missing. With that baseline now available, departures from lay understanding become transparent rather than hidden, a choice to be justified, not a fact to be assumed. Properly cabined, the generative reasonable person may become a dictionary for reasonableness judgments.

cs.CY↗

arXiv2023

Generative Interpretation

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 LLMs 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.

cs.CL↗