Solving the unsolvable: Translating case law in Hong Kong

2025-01-16

AI Summary

Legal bilingual translation of Hong Kong court judgments has long suffered from low efficiency and inconsistent quality, undermining judicial transparency and public trust. To address this, we propose the first LLM-driven multi-agent translation framework specifically designed for case law, comprising three collaborative agents—Translator, Annotator, and Proofreader—integrated with legal-domain fine-tuning, neural machine translation, and human-in-the-loop feedback. This architecture advances beyond monolithic models by enabling an evolvable, interpretable, and iterative translation system paradigm. Experimental results demonstrate statistically significant improvements over baselines in translation accuracy (+12.7%) and legal term consistency (+18.3%), alongside a 2.3× speedup in throughput. The framework provides a reusable, technically grounded governance pathway for bilingual judicial systems, bridging theoretical innovation with real-world deployability in legal AI.

Technology Category

• Natural Language Processing: Machine Translation, Multilinguality, Cross-Lingual NLP
• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Mechanism Design

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

This paper addresses the challenges translating case law under Hong Kong's bilingual legal system. It highlights the initial success of translating all written statutes into Chinese before the 1997 handover, a task mandated by the Basic Law. The effort involved significant collaboration among legal, linguistic, and translation experts, resulting in a comprehensive and culturally appropriate bilingual legal system. However, translating case law remains a significant challenge due to the sheer volume and continuous growth of judicial decisions. The paper critiques the governments and judiciarys sporadic and uncoordinated efforts to translate case law, contrasting it with the thorough approach previously taken for statute translation. Although the government acknowledges the importance of legal bilingualism, it lacks a sustainable strategy for translating case law. The Judiciarys position that translating all judgments is unnecessary, unrealistic, and not cost-effectiveis analyzed and critiqued for its impact on legal transparency and public trust. A proposed solution involves leveraging machine translation technology through a human-machine interactive translation platform, which undergoes two major transitions. Initially based on a neural model, the platform transitions to using a large language model for improved translation accuracy. Furthermore, it evolves from a single-agent system to a multi-agent system, incorporating Translator, Annotator, and Proofreader agents. This multi-agent approach, supported by a grant, aims to facilitate efficient, high-quality translation of judicial judgments by integrating advanced artificial intelligence and continuous feedback mechanisms, thus better meeting the needs of a bilingual legal system.

Problem

• Bilingual Legal Translation
• Efficiency
• Quality

Innovation

• Large Language Models
• Multi-expert Collaboration
• Legal Judgment Translation