Nigerian Legal Corpus released: cleaned constitutional and legal texts for RAG and legal NLP
saheedniyi_02 · x · 2026-11-04
Developer Yusuf Sanni released the Nigerian Legal Corpus, a cleaned and structured dataset for information retrieval, RAG, semantic search and legal NLP, covering the 1999 Constitution, Electoral Act, Criminal Code Act and Lagos Tenancy Law. It's open on GitHub and Hugging Face, alongside Barrister, a legal retrieval app built on top of it.
More from Research
- Georgia Tech Dynamical ML Group recruiting on diffusion LMs for Fall 2027 — LucaAmb · 2026-11-04
- DeepMind adds Cheminformatics Skills to Antigravity for retrosynthesis and enzyme design — jueseph · 2026-11-04
- Artificial Analysis ships CritPt v2 grading server, regrades all models with max 1-point shifts — ArtificialAnlys · 2026-11-04
- Vector and Waterloo's Chrysalis makes students teach the AI to finish assignments — VectorInst · 2026-11-04
- Neuro for AI & AI for Neuro workshop at AAAI 2027 opens call for papers, due Nov 20, 2026 — naturecomputes · 2026-11-04
- Multimodal benchmarks should undergo blind filtering by default, researcher argues — cwolferesearch · 2026-11-04