LegalPincite: Multi-level Legal Information Retrieval Dataset

Hugging Face Daily Papers Papers
legal-ir dataset information-retrieval cjeu legal-nlp

Summary

Introduces LegalPincite, a large-scale legal information retrieval dataset built from CJEU judgments, featuring masked queries, full corpora, and paragraph-level citation annotations to enable multi-level retrieval evaluation.

A common task in legal Information Retrieval (IR) is to find relevant legal sources from case-law collections. While legal practice often requires pinpoint citations (pincites) to specific case paragraphs, most existing public legal IR datasets lack paragraph-level citation annotations. Yet, publicly available datasets with such information contain data leakage in the query text and exclude paragraphs that are neither citing nor cited from the corpora, creating an unrealistic and oversimplified retrieval setting, potentially leading to inflated performance. To address these limitations, we contribute a large-scale legal IR dataset constructed from Court of Justice of the European Union (CJEU) judgments. The dataset contains: (i) masked case/paragraph queries, with removed citation information; (ii) a corpus that includes all paragraphs; and (iii) case- and paragraph-level ground-truth citations, with partial human expert validation. Our dataset supports both the development and rigorous evaluation of legal IR methods, at multiple query-document levels (case-to-case, paragraph-to-case, and paragraph-to-paragraph retrieval). Link to dataset: https://huggingface.co/datasets/theresiavr/legalpincite
Original Article
View Cached Full Text

Cached at: 08/05/26, 05:46 PM

Paper page - LegalPincite: Multi-level Legal Information Retrieval Dataset

Source: https://huggingface.co/papers/2608.03756 Published on Aug 4

·

Submitted byhttps://huggingface.co/theresiavr

TVRon Aug 5

Abstract

AcommontaskinlegalInformationRetrieval(IR)istofindrelevantlegalsourcesfromcase-lawcollections.Whilelegalpracticeoftenrequirespinpointcitations(pincites)tospecificcaseparagraphs,mostexistingpubliclegalIRdatasetslackparagraph-levelcitationannotations.Yet,publiclyavailabledatasetswithsuchinformationcontaindataleakageinthequerytextandexcludeparagraphsthatareneithercitingnorcitedfromthecorpora,creatinganunrealisticandoversimplifiedretrievalsetting,potentiallyleadingtoinflatedperformance.Toaddresstheselimitations,wecontributealarge-scalelegalIRdatasetconstructedfromCourtofJusticeoftheEuropeanUnion(CJEU)judgments.Thedatasetcontains:(i)maskedcase/paragraphqueries,withremovedcitationinformation;(ii)acorpusthatincludesallparagraphs;and(iii)case-andparagraph-levelground-truthcitations,withpartialhumanexpertvalidation.OurdatasetsupportsboththedevelopmentandrigorousevaluationoflegalIRmethods,atmultiplequery-documentlevels(case-to-case,paragraph-to-case,andparagraph-to-paragraphretrieval).Linktodataset:https://huggingface.co/datasets/theresiavr/legalpincite

View arXiv pageView PDFProject pageGitHubAdd to collection

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.03756 in a model README.md to link it from this page.

Datasets citing this paper1

#### theresiavr/legalpincite Viewer• Updated35 minutes ago • 1.47M • 320 • 1

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.03756 in a Space README.md to link it from this page.

Collections including this paper1

Similar Articles

Automatic Construction of a Legal Citation Graph from 100 Million Ukrainian Court Decisions: Large-Scale Extraction, Topological Analysis, and Ontology-Driven Clustering

arXiv cs.CL

This paper constructs the first large-scale citation graph from 100.7 million Ukrainian court decisions, extracting over 500 million citation links. It demonstrates that the citation structure can automatically recover legal domain boundaries and predict legislative importance with near-perfect accuracy, and releases the pipeline and data as open resources.

CanLegalRAGBench: Evaluating Retrieval-Augmented Generation on Canadian Case Law

arXiv cs.CL

Introduces CanLegalRAGBench, a benchmark for evaluating retrieval-augmented generation on Canadian case law using realistic queries and expert-annotated answers. The evaluation reveals sensitivity to design choices, competitiveness of open-source embedding models, and persistent hallucinations in generated answers.