EG-VAR: Lean 4-Based Architecture Eliminates LLM Hallucination in Empirical Reasoning

Jul 15, 2026

Researchers introduce EG-VAR, a Lean 4-based tool-calling architecture that ensures every verified output is grounded in attested tool calls and kernel-checked inference, thereby eliminating unsupported claims. On a subset of TableBench numerical reasoning tasks (n=120), EG-VAR achieves perfect accuracy (120/120) compared to a 95% baseline, and maintains 100% source-faithfulness on stress tests where baselines drop to 80-90%. The system also provides explicit audit trails for abstentions and formalization errors.

Why it matters: EG-VAR offers a practical and auditable approach to eliminating LLM hallucination in empirical inference, potentially transforming trustworthiness in high-stakes AI applications.

Full story at: arXiv Computers and Society ↗