AI RESEARCH
Falkor-IRAC: Graph-Constrained Generation for Verified Legal Reasoning in Indian Judicial AI
arXiv CS.CL
•
ArXi:2605.14665v1 Announce Type: cross Legal reasoning is not semantic similarity search. A court judgment encodes constrained symbolic reasoning: precedent propagation, procedural state transitions, and statute-bound inference. These are properties that vector-based retrieval-augmented generation (RAG) cannot faithfully represent. Hallucinated precedents, outdated statute citations, and uned reasoning chains remain persistent failure modes in LLM-based legal AI, with real consequences for access to justice in high-caseload jurisdictions such as India.