AI RESEARCH
Citation Grounding: Detecting and Reducing LLM Citation Hallucinations via Legal Citation Graphs
arXiv CS.CL
•
ArXi:2606.00898v1 Announce Type: new Large language models systematically hallucinate legal citations -- fabricating statute references, citing repealed provisions, and confusing jurisdictions -- yet no automated method exists to measure or reduce this behavior at scale. We propose citation grounding (CG), a metric that verifies LLM-generated legal citations against a ground-truth citation graph extracted from 100.8M Ukrainian court decisions (502M edges, 21,736 unique statute nodes