LegalPincite: Multi-level Legal Information Retrieval Dataset

LegalPincite is a large-scale legal information retrieval dataset built from CJEU judgments to test search methods at multiple levels: case, paragraph, and paragraph-to-paragraph. It includes ground truth citations and rigorous cleaning to prevent data leakage. This resource allows researchers to evaluate how well systems find relevant legal citations across different query complexities.

Open the full episode

More from AI Radio