Multi-Label Delegation Target Identification in Japanese Law
Abstract
AbstractLegal 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.