Legal systems often employ legislative drafting practices in which higher-level laws delegate detailed regulations to lower-level laws. In particular, when a single provision delegates authority to multiple lower-level laws, readers must cross-reference many related provisions scattered across the entire bodies of law, imposing a substantial cognitive burden. Reflecting this real-world problem, this work proposes a novel multi-label delegation target identification task to identify all the delegated provisions corresponding to an input provision, with the focus on Japanese law. We construct pipeline systems combining a candidate retriever and a candidate classifier, using language models with diverse architectures. Experimental results show that adopting a cross-encoder-based binary classifier as a candidate classifier improves performance at finer granularities, establishing a solid baseline for the task. Furthermore, our comprehensive analyses reveal the remaining challenges in achieving sufficient performance on instances with many delegated provisions and identify typical error types, providing a foundation for future improvement.

The legal systems have a hierarchical structure, and a higher-level law often authorizes a lower-level law to implement detailed provisions, which is called delegation. When interpreting legal texts with delegation, readers must repeatedly consult the lower-level laws that stipulate the detailed provisions, imposing a substantial workload. Therefore, it is necessary to develop a system that enables readers to instantly refer to relevant laws in delegation. However, manually annotating delegation is difficult because it requires extensive legal expertise, careful reading of numerous legal texts, and continuous adaptation to newly enacted laws. In this study, we focus on Japanese law and develop a two-stage pipeline system for automatic delegation annotation. First, we extract keywords that indicate delegation using a named entity recognition approach. Second, we identify the delegated provision corresponding to each keyword as an entity disambiguation task. In our experiments, the proposed system demonstrates sufficient performance to assist manual annotation in practice.

Entity linking (EL) aims to disambiguate named entities in text by mapping them to the appropriate entities in a knowledge base. However, it is difficult to use some EL methods, as they sometimes have issues in reproducibility due to limited maintenance or the lack of official resources.To address this, we introduce , a unified library for using and developing entity linking systems through a unified interface. Our library flexibly integrates various candidate retrievers and re-ranking models, making it easy to compare and use any entity linking methods within a unified framework. In addition, it is designed with a strong emphasis on API usability, making it highly extensible, and it supports both command-line tools and APIs. Our code is available on GitHub and is also distributed via PyPI under the MIT-license. The video is available on YouTube.