TransLaw: A Large-Scale Dataset and Multi-Agent Benchmark Simulating Professional Translation of Hong Kong Case Law

TL;DR

TransLaw introduces a multi-agent framework with specialized legal resources and iterative feedback to improve Hong Kong legal translation accuracy, outperforming baseline models and validated by human evaluation.

Contribution

It presents a novel multi-agent translation framework incorporating legal glossaries, RAG, and feedback, specifically designed for Hong Kong case law translation.

Findings

TransLaw outperforms single-agent models across multiple benchmarks.

Human evaluation shows high legal and structural accuracy, but room remains for stylistic naturalness.

Benchmarking on HKCFA Judgment 97-22 dataset demonstrates effectiveness.

Abstract

Hong Kong case law translation presents significant challenges: manual methods suffer from high costs and inconsistent quality, while both traditional machine translation and approaches relying solely on Large Language Models (LLMs) often fail to ensure legal terminology accuracy, culturally embedded nuances, and strict linguistic structures. To overcome these limitations, this study proposes TransLaw, a multi-agent framework that decomposes translation into word-level expression, sentence-level translation, and multidimensional review, integrating a specialized Hong Kong legal glossary database, Retrieval-Augmented Generation (RAG), and iterative feedback. Experiments on our newly constructed HKCFA Judgment 97-22 dataset, benchmarking 13 open-source and commercial LLMs, demonstrate that TransLaw significantly outperforms single-agent baselines across all evaluated models. Human evaluation confirms the framework's effectiveness in terms of legal semantic accuracy, structural coherence, and stylistic fidelity, while noting that it still trails human experts in contextualizing complex terminology and stylistic naturalness.