We demonstrate that the ability to produce relevant (goal‑directed) text is architecturally distinct from the ability to produce coherent (statistically fluent) text. Using a controlled text‑generation simulation, we show that a unidirectional Markovian language model achieves 0% relevance on novel compositional goals, while bidirectional and multidirectional models (Seq2Seq LSTM and Transformer) achieve 100% relevance. The clean 0% vs. 100% split provides the first empirical proof that relevance requires non‑Markovian conditioning, and that coherence and relevance are fundamentally different dimensions of text quality.