CrossLex evaluates LLMs on same-fact, cross-jurisdictional legal reasoning with citation grounding, showing that models often answer correctly but fail to bind conclusions and citations to the right legal system.
Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks , volume =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CrossLex: A Source-Grounded Benchmark for Cross-Jurisdictional Legal Reasoning in Large Language Models
CrossLex evaluates LLMs on same-fact, cross-jurisdictional legal reasoning with citation grounding, showing that models often answer correctly but fail to bind conclusions and citations to the right legal system.