Temporal reasoning in legal texts is important for applications like case law analysis and compliance monitoring. However, existing datasets lack expert language evaluation, leaving a gap in understanding how LLMs manage event ordering in legal contexts. We introduce LexTime, the first dataset designed to evaluate LLMs' event ordering capabilities in legal language, consisting of 512 instances from U.S. Federal Complaints with annotated event pairs and their temporal relations. Our findings show that (1) LLMs are more accurate on legal event ordering than on narrative (up to +10.5%); (2) longer input contexts and implicit events boost accuracy, reaching 80.8% for implicit-explicit event pairs; (3) legal linguistic complexities and nested clauses remain a challenge. We investigate how context length, explicit vs implicit event pairs, and legal language features affect model performance, demonstrating the need for specific modeling strategies to enhance temporal event reasoning.
View on arXiv@article{barale2025_2506.04041,
title={ LexTime: A Benchmark for Temporal Ordering of Legal Events },
author={ Claire Barale and Leslie Barrett and Vikram Sunil Bajaj and Michael Rovatsos },
journal={arXiv preprint arXiv:2506.04041},
year={ 2025 }
}