Generative Gap Filling

• URL: http://arxiv.org/abs/2608.21401v1
• Date: Fri, 07 Aug 2026 05:19:02 GMT
• Title: Generative Gap Filling
• Abstract summary: Most contract litigation turns on contracts that imperfectly record parties' bargains.<n>When the parties' dispute can't be solved by interpreting the text, courts fill the gap.<n>Despite generations of work, courts have no real alternative to such unruly methods.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• A Formal Limitation on Learning Human Language From Textual Corpora [54.22186267212778]
  We derive upper bounds on the probability that a decoder recovers a speaker's intended meaning from a representation of the utterance.<n>Experiments on artificial languages, Mandarin zero-pronoun resolution, and color reference provide empirical evidence in support of the theory.
  arXiv  Detail & Related papers  (2026-08-28T17:38:24Z)
• Sharding Prevents LLM Oversight Failures and Adversarial Exploitation [45.380649793616705]
  Sharding partitions requirements into smaller groups, assigns each group to a separate call, and aggregates the verdicts.<n>We find that a sharded weaker judge can outperform a more capable holistic judge and match that judge even when the latter receives the panel's full budget.
  arXiv  Detail & Related papers  (2026-08-05T18:21:21Z)
• Where Experts Disagree, Models Fail: Detecting Implicit Legal Citations in French Court Decisions [3.8449738927037207]
  We focus on implicit citation of the French Civil Code in first-instance court decisions.<n>We show that expert disagreement predicts model failures.<n>Despite these limits, reframing the task as top-k ranking and leveraging multi-model consensus yields 76% precision at k = 200 in an unsupervised setting.
  arXiv  Detail & Related papers  (2026-03-24T09:10:57Z)
• Ambiguity is the last thing you need [0.0]
  Clear legal language forms the backbone of a contract for numerous reasons. Disputes often arise between contract parties where ambiguous language has been used. Unambiguous language can also be important where there is an imbalance of bargaining strength between the parties.
  arXiv  Detail & Related papers  (2024-10-26T16:35:45Z)
• Towards Explainability in Legal Outcome Prediction Models [64.00172507827499]
  We argue that precedent is a natural way of facilitating explainability for legal NLP models. By developing a taxonomy of legal precedent, we are able to compare human judges and neural models. We find that while the models learn to predict outcomes reasonably well, their use of precedent is unlike that of human judges.
  arXiv  Detail & Related papers  (2024-03-25T15:15:41Z)
• Towards Mitigating Perceived Unfairness in Contracts from a Non-Legal Stakeholder's Perspective [2.9748898344267776]
  We conduct an empirical study to analyze the perspectives of different stakeholders regarding contractual fairness. We then investigate the ability of Pre-trained Language Models (PLMs) to identify unfairness in contractual sentences.
  arXiv  Detail & Related papers  (2023-12-03T13:52:32Z)
• Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness? [53.98071556805525]
  Neural language models (LMs) can be used to evaluate the truth of factual statements. They can be queried for statement probabilities, or probed for internal representations of truthfulness. Past work has found that these two procedures sometimes disagree, and that probes tend to be more accurate than LM outputs. This has led some researchers to conclude that LMs "lie" or otherwise encode non-cooperative communicative intents.
  arXiv  Detail & Related papers  (2023-11-27T18:59:14Z)
• Generative Interpretation [0.0]
  We introduce generative interpretation, a new approach to estimating contractual meaning using large language models. We show that AI models can help factfinders ascertain ordinary meaning in context, quantify ambiguity, and fill gaps in parties' agreements.
  arXiv  Detail & Related papers  (2023-08-14T02:59:27Z)
• Formally Verifying a Real World Smart Contract [52.30656867727018]
  We search for a tool capable of formally verifying a real-world smart contract written in a recent version of Solidity. In this article, we present our search for a tool capable of formally verifying a real-world smart contract written in a recent version of Solidity.
  arXiv  Detail & Related papers  (2023-07-05T14:30:21Z)
• Language of Bargaining [60.218128617765046]
  We build a novel dataset for studying how the use of language shapes bilateral bargaining. Our work also reveals linguistic signals that are predictive of negotiation outcomes.
  arXiv  Detail & Related papers  (2023-06-12T13:52:01Z)
• Exploiting Contrastive Learning and Numerical Evidence for Confusing Legal Judgment Prediction [46.71918729837462]
  Given the fact description text of a legal case, legal judgment prediction aims to predict the case's charge, law article and penalty term. Previous studies fail to distinguish different classification errors with a standard cross-entropy classification loss. We propose a moco-based supervised contrastive learning to learn distinguishable representations. We further enhance the representation of the fact description with extracted crime amounts which are encoded by a pre-trained numeracy model.
  arXiv  Detail & Related papers  (2022-11-15T15:53:56Z)
• Detecting Logical Relation In Contract Clauses [94.85352502638081]
  We develop an approach to automate the extraction of logical relations between clauses in a contract. The resulting approach should help contract authors detecting potential logical conflicts between clauses.
  arXiv  Detail & Related papers  (2021-11-02T19:26:32Z)
• ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts [39.75232199445175]
  We propose "document-level natural language inference (NLI) for contracts" A system is given a set of hypotheses and a contract, and it is asked to classify whether each hypothesis is "entailed by", "contradicting to" or "not mentioned by" (neutral to) the contract. We release the largest corpus to date consisting of 607 annotated contracts.
  arXiv  Detail & Related papers  (2021-10-05T03:22:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.