HKJudge: New Annotated Corpus of Hong Kong Court Judgments Released for Legal AI Research
Researchers have introduced HKJudge, the first sentence-level expert-annotated legal discourse corpus covering Hong Kong court judgments across all five levels of the court hierarchy. The dataset comprises approximately 290,000 sentences and 6.5 million tokens, annotated by ten legal linguistics experts using a two-tier discourse schema with 26 rhetorical roles and three sentencing elements. The resource aims to advance computational modeling of legal judgment structure and support future work on legal judgment prediction.
The HKJudge dataset addresses a gap in legal NLP research by providing the first expert-annotated corpus specifically designed for discourse analysis of Hong Kong criminal judgments. Spanning all five levels of Hong Kong's court hierarchy, the corpus contains roughly 290,000 sentences and 6.5 million tokens, fully labeled by ten legal linguistics experts. Annotations follow a two-tier schema: at the sentence level, each sentence receives one of 26 rhetorical roles capturing what facts a court finds, how it reasons, and what it rules; at the span level, sentences are further tagged with sentencing elements including charge, imprisonment term, and fine. Inter-annotator agreement reached a Cohen's kappa of 0.8, indicating strong reliability. The authors benchmarked four BERT-based models, two open-source large language models under zero-shot and fine-tuning conditions, and four commercial LLMs on rhetorical role classification and legal element extraction tasks. The dataset and associated code have been made publicly available to support further research.
What's missing
The study focuses exclusively on criminal judgments and does not address civil, administrative, or other case types, which may limit generalizability. It is also unclear how well models trained on HKJudge would transfer to other common law jurisdictions with different judgment conventions.
What different sources said
- arXiv cs.CLCenter
HKJudge: A Legal Discourse-Annotated Corpus for Interpreting What Courts Find, How They Reason, and What They Rule
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.