AI / LLM / Agents
JurisGPT
Citation-grounded legal assistant for Indian startup and corporate law — RAG over 47,867 legal documents with inline citations and confidence badges. Published as an IEEE research paper.
The problem
India's 100,000+ startups can't afford specialist counsel, and general-purpose LLMs hallucinate legal authority — commercial legal AI tools show 17–33% hallucination rates. Advice built on an invented section or repealed provision causes real regulatory damage.
The solution
Built a citation-grounded RAG assistant over a maintained corpus of 47,867 Indian legal documents (Companies Act 2013 + nine further statutes). Hybrid BM25 + lexical retrieval fused with weighted Reciprocal Rank Fusion, source-constrained generation with Claude, and every answer carrying inline citations, confidence badges, and limitation statements.
Key features
Impact
Recall@5 of 0.84 and MRR of 0.95 (hybrid config)
80% citation-faithful answers, 2.5% severe hallucination
Published IEEE paper + live at jurisgpt.me
Learnings
“Retrieval quality in legal RAG is corpus-bound, not retriever-bound — and generic MS MARCO rerankers actively hurt legal retrieval (nDCG@5 down 8.7–16.3 points). Rigorous evaluation with significance testing matters more than fancy components.”