# HKJudge: A Legal Discourse-Annotated Corpus for Interpreting What Courts Find, How They Reason, and What They Rule

arXiv: https://arxiv.org/abs/2606.06679 · HTML: https://mlsanity.com/paper/2606.06679/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 62 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Builds on (most cited first, 21 of 21)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review](https://mlsanity.com/paper/2103.06268/) (2021)
- [CAIL2018: A Large-Scale Legal Dataset for Judgment Prediction](https://mlsanity.com/paper/1807.02478/) (2018)
- [ILDC for CJPE: Indian Legal Documents Corpus for Court Judgment Prediction and Explanation](https://mlsanity.com/paper/2105.13562/) (2021)
- [AgentsCourt: Building Judicial Decision-Making Agents with Court Debate Simulation and Legal Knowledge Augmentation](https://mlsanity.com/paper/2403.02959/) (2024)
- [Identification of Rhetorical Roles of Sentences in Indian Legal Judgments](https://mlsanity.com/paper/1911.05405/) (2019)
- [LawLLM: Law Large Language Model for the US Legal System](https://mlsanity.com/paper/2407.21065/) (2024)
- [Corpus for Automatic Structuring of Legal Documents](https://mlsanity.com/paper/2201.13125/) (2022)
- [Discourse Analysis via Questions and Answers: Parsing Dependency Structures of Questions Under Discussion](https://mlsanity.com/paper/2210.05905/) (2022)
- [LegalReasoner: Step-wised Verification-Correction for Legal Judgment Reasoning](https://mlsanity.com/paper/2506.07443/) (2025)
- [LegalSeg: Unlocking the Structure of Indian Legal Judgments Through Rhetorical Role Classification](https://mlsanity.com/paper/2502.05836/) (2025)
- [Multilingual Source Tracing of Speech Deepfakes: A First Benchmark](https://mlsanity.com/paper/2508.04143/) (2025)
- [Fake-Mamba: Real-Time Speech Deepfake Detection Using Bidirectional Mamba as Self-Attention's Alternative](https://mlsanity.com/paper/2508.09294/) (2025)
- [WaveSP-Net: Learnable Wavelet-Domain Sparse Prompt Tuning for Speech Deepfake Detection](https://mlsanity.com/paper/2510.05305/) (2025)
- [Talking Point based Ideological Discourse Analysis in News Events](https://mlsanity.com/paper/2504.07400/) (2025)
- [Improving Legal Judgement Prediction in Romanian with Long Text Encoders](https://mlsanity.com/paper/2402.19170/) (2024)
- [WaveScat: Wavelet Scattering Front-Ends with Self-Supervised Features for Speech Deepfake Detection](https://mlsanity.com/paper/2602.02980/) (2026)
- [TransLaw: A Large-Scale Dataset and Multi-Agent Benchmark Simulating Professional Translation of Hong Kong Case Law](https://mlsanity.com/paper/2507.00875/) (2025)
- [Analyzing Hong Kong's Legal Judgments from a Computational Linguistics point-of-view](https://mlsanity.com/paper/2305.02558/) (2023)
- [Disentangling Speaker Traits for Deepfake Source Verification via Chebyshev Polynomial and Riemannian Metric Learning](https://mlsanity.com/paper/2603.21875/) (2026)

## Abstract (arXiv)

Court judgments are central to legal practice and jurisprudence, yet discourse analysis of Hong Kong judgments has received limited attention, owing largely to the absence of expert-annotated corpora. We introduce the Hong Kong Judgment Discourse Dataset (HKJudge), the first sentence-level expert-annotated legal discourse corpus. HKJudge includes criminal judgments across all five levels of HK's court hierarchy, comprising ~290k sentences and ~6.5 million tokens, fully annotated by legal linguistics experts. We design a two-tier discourse schema that captures what facts a court finds, how it reasons, and what it rules. At the sentence level, each sentence is assigned one of 26 rhetorical roles. At the span level, sentences are further annotated with three sentencing elements (charge, imprisonment term, fine). Ten legal linguistics annotators produced the annotations with an inter-annotator agreement of kappa = 0.8. We formulate two tasks on HKJudge, termed rhetorical role classification and legal element extraction, and provide the first benchmark evaluation of four BERT-based models, two open-source LLMs under zero-shot and fine-tuning settings, and four commercial LLMs on both tasks. Our work demonstrates the value of sentence-level discourse annotation for modeling the structure of HK judgments and provides a rich data foundation for future work on legal judgment prediction. The HKJudge dataset and code are available at https://github.com/xuanxixi/HKJudge.