Beyond Factual Accuracy: Evaluating Global Reasoning Integrity in RAG Systems with LogicScore

Current evaluation methods for Retrieval Augmented Generation (RAG) suffer from $\mathit{\text{factual}}\mathit{\text{myopia}}$: they relentlessly emphasize factual accuracy yet neglect global logical integrity in long-form answer generation. This drives models to force unnatural connections, producing factually grounded yet logically incoherent responses with unaddressed gaps, ambiguous links, or redundant premises. To mitigate this, we present $\text{textsc}LogicScore$, shifting from local, fact-by-fact assessment to rigorous global reasoning scrutiny. Grounded in Horn Rules, our approach integrates a backward verification mechanism to systematically evaluate three key reasoning dimensions: $\mathit{\text{Completeness}}$ (logically sound deduction), $\mathit{\text{Essentiality}}$ (non-redundancy), and $\mathit{\text{Determinateness}}$ (consistent answer entailment). Extensive experiments across three multi-hop QA datasets (HotpotQA, MusiQue, and 2WikiMultiHopQA) and over 20 LLMs (including GPT-5, Gemini-3-Pro, LLaMA3, and task-specific tuned models) reveal a critical capability gap: leading models often achieve high factual accuracy (e.g., 92.85% precision for Gemini-3 Pro) but struggle with global reasoning quality (e.g., 35.11% Essentiality for Gemini-3 Pro). Our work establishes a robust standard for logical evaluation, highlighting the need to prioritize reasoning coherence alongside factual grounding in LLM development.