llm-verification

This paper presents AuditFlow, a graph-grounded multi-agent framework that uses executable symbolic environments for structured financial reporting verification, achieving 82.09% audit accuracy on a FinAuditing-derived sample under GPT-5.5.

This paper introduces CiteTracer, a multi-agent framework for detecting citation hallucinations in LLM-generated scientific writing, achieving high accuracy on synthetic and real-world benchmarks.