LeCoPCR: Legal Concept-guided Prior Case Retrieval for European Court of Human Rights cases

TL;DR

This work tackles prior case retrieval (PCR) in the European Court of Human Rights by making semantic intent explicit through a legal-concept generation step. It introduces LeCoPCR, which uses a seq2seq model trained with weak supervision to extract key legal concepts from case reasoning and then applies Determinantal Point Process (DPP) to select a diverse, high-quality concept set for augmenting the query. The augmented query improves retrieval performance for both lexical and neural retrievers (e.g., BM25 and Longformer), with DPP-based concept extraction and a hybrid training regime offering robustness to noisy concept generation. Experiments on the ECtHR-PCR dataset show recall and MAP gains, and case studies illustrate how generated concepts reflect meaningful legal intents that guide precedent selection and enhance explainability. Overall, LeCoPCR provides a principled way to encode legal reasoning into retrieval, with potential applicability to other jurisdictions and future integration of citation networks and temporal dynamics.

Abstract

Prior case retrieval (PCR) is crucial for legal practitioners to find relevant precedent cases given the facts of a query case. Existing approaches often overlook the underlying semantic intent in determining relevance with respect to the query case. In this work, we propose LeCoPCR, a novel approach that explicitly generate intents in the form of legal concepts from a given query case facts and then augments the query with these concepts to enhance models understanding of semantic intent that dictates relavance. To overcome the unavailability of annotated legal concepts, we employ a weak supervision approach to extract key legal concepts from the reasoning section using Determinantal Point Process (DPP) to balance quality and diversity. Experimental results on the ECtHR-PCR dataset demonstrate the effectiveness of leveraging legal concepts and DPP-based key concept extraction.