2024/09/27 by T. Y. S. S Santosh, Santosh, T. Y. S. S., Mohamed Hesham Elganayni +5 · 2 citations
Social Sciences · #Computation and Language (cs.CL) #European Criminal Justice and Data Protection #European and International Law Studies #FOS: Computer and information sciences #Judicial and Constitutional Studies
paper · pdf · doi:10.48550/arxiv.2409.18644
openalex publication_date 2024/09/27 · openalex created_date 2024/10/27 · openalex updated_date 2026/07/28
Inspired by the legal doctrine of stare decisis, which leverages precedents (prior cases) for informed decision-making, we explore methods to integrate them into LJP models. To facilitate precedent retrieval, we train a retriever with a fine-grained relevance signal based on the overlap ratio of alleged articles between cases. We investigate two strategies to integrate precedents: direct incorporation at inference via label interpolation based on case proximity and during training via a precedent fusion module using a stacked-cross attention model. We employ joint training of the retriever and LJP models to address latent space divergence between them. Our experiments on LJP tasks from the ECHR jurisdiction reveal that integrating precedents during training coupled with joint training of the retriever and LJP model, outperforms models without precedents or with precedents incorporated only at inference, particularly benefiting sparser articles.