Solving the Unsolvable: Translating Case Law in Hong Kong
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 52 of its 94 references that are in the map. First posted on arXiv 16 Jan 2025.
Builds on
52 of 94 references.
References · 52
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
- 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
- 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
- 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
- 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
- 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
- 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
- 2023Qwen Technical Reportcited by 3,273
- 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
- 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
38 more
- 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,968
- 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
- 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
- 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
- 2023PaLM 2 Technical Reportcited by 1,154
- 2022GLM-130B: An Open Bilingual Pre-trained Modelcited by 837
- 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 752
- 2023The Flan Collection: Designing Data and Methods for Effective Instruction Tuningcited by 734
- 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 574
- 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 554
- 2024From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judgecited by 480
- 2023Cognitive Architectures for Language Agentscited by 422
- 2023PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimizationcited by 311
- 2023How Language Model Hallucinations Can Snowballcited by 310
- 2022Social Simulacra: Creating Populated Prototypes for Social Computing Systemscited by 300
- 2023xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detectioncited by 260
- 2023Prompting Large Language Model for Machine Translation: A Case Studycited by 247
- 2023Large Language Model Alignment: A Surveycited by 241
- 2023An Overview of Catastrophic AI Riskscited by 214
- 2023RoCo: Dialectic Multi-Robot Collaboration with Large Language Modelscited by 171
- 2023Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Gamecited by 148
- 2023Self-correcting LLM-controlled Diffusion Modelscited by 112
- 2023Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplationcited by 102
- 2023A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directionscited by 101
- 2023Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debatecited by 94
- 2023A Survey on Fairness in Large Language Modelscited by 91
- 2022BioRED: A Rich Biomedical Relation Extraction Datasetcited by 84
- 2023Contrastive Preference Learning: Learning from Human Feedback without RLcited by 77
- 2023Identifying and Mitigating Vulnerabilities in LLM-Integrated Applicationscited by 54
- 2024(Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Textscited by 49
- 2023Welfare Diplomacy: Benchmarking Language Model Cooperationcited by 43
- 2024AI Hallucinations: A Misnomer Worth Clarifyingcited by 34
- 2023Let GPT be a Math Tutor: Teaching Math Word Problem Solvers with Customized Exercise Generationcited by 27
- 2024Debatrix: Multi-dimensional Debate Judge with Iterative Chronological Analysis Based on LLMcited by 21
- 2024Retrieve-Plan-Generation: An Iterative Planning and Answering Framework for Knowledge-Intensive LLM Generationcited by 15
- 2023Are you in a Masquerade? Exploring the Behavior and Impact of Large Language Model Driven Social Bots in Online Social Networkscited by 13
- 2024Multimodal LLM Enhanced Cross-lingual Cross-modal Retrievalcited by 13
- 2024Large Language Model Capabilities in Perioperative Risk Prediction and Prognosticationcited by 11
50 most cited of 52 All 52 (JSON)
Built on by
Citing papers per year: 2025: 3.
3 papers.
- 2025Multilingual Source Tracing of Speech Deepfakes: A First Benchmarkcited by 7
- 2025TransLaw: A Large-Scale Dataset and Multi-Agent Benchmark Simulating Professional Translation of Hong Kong Case Lawcited by 2
- 2025AI agents may be worth the hype but not the resources (yet): An initial exploration of machine translation quality and costs in three language pairs in the legal and news domainscited by 0
- 2025Multilingual Source Tracing of Speech Deepfakes: A First Benchmark6 Aug 2025
- 2025TransLaw: A Large-Scale Dataset and Multi-Agent Benchmark Simulating Professional Translation of Hong Kong Case Law1 Jul 2025
- 2025AI agents may be worth the hype but not the resources (yet): An initial exploration of machine translation quality and costs in three language pairs in the legal and news domains2 May 2025