# Generative Interpretation

arXiv: https://arxiv.org/abs/2308.06907 · HTML: https://mlsanity.com/paper/2308.06907/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 38 references that are in the map.
- First posted on arXiv 14 Aug 2023.

## Builds on (most cited first, 1 of 1)

- [On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective](https://mlsanity.com/paper/2302.12095/) (2023)

## Built on by (most cited first, 9 of 9)

- [LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models](https://mlsanity.com/paper/2308.11462/) (2023)
- [Securing Large Language Models: Addressing Bias, Misinformation, and Prompt Attacks](https://mlsanity.com/paper/2409.08087/) (2024)
- [Challenges for Generative AI in Legal Reasoning](https://mlsanity.com/paper/2508.18880/) (2025)
- [Automating Legal Interpretation with LLMs: Retrieval, Generation, and Evaluation](https://mlsanity.com/paper/2501.01743/) (2025)
- [Prompting from the bench: Large-scale pretraining is not sufficient to prepare LLMs for ordinary meaning analysis](https://mlsanity.com/paper/2510.25356/) (2025)
- [Bye-bye, Bluebook? Automating Legal Drudgery With AI-Augmented Rule Following](https://mlsanity.com/paper/2505.02763/) (2025)
- [Ambiguity Collapse by LLMs: A Taxonomy of Epistemic Risks](https://mlsanity.com/paper/2603.05801/) (2026)
- [The Material Contracts Corpus](https://mlsanity.com/paper/2504.02864/) (2025)
- [Directing large language models to follow the letter or spirit of the law](https://mlsanity.com/paper/2609.23083/) (2026)

## Abstract (arXiv)

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.