This study introduces LMAT-ND (Llama-7B Enhanced Meta-Attention Transformer for News Detection) to distinguish AI-generated from human-authored news by integrating a Meta-Attention Mechanism and Dynamic Multi-Head Attention to capture linguistic distinctions, alongside a Dual-Classification Layer for optimized classification. LMAT-ND leverages Meta-Attention to dynamically adjust attention distribution, enhancing context-aware feature extraction, while the Dynamic Multi-Head Attention refines classification by emphasizing context-sensitive features. Additionally, the Dual-Classification Layer employs a two-stage strategy, integrating semantic and linguistic details to improve predictions. Experiments demonstrate that LMAT-ND outperforms GPT-3 and Llama-7B in accuracy, recall, and F1-score, with ablation studies confirming the Meta-Attention Mechanism and Dual-Classification Layer's impact. Performance remains strong across COCO and FakeImage datasets, validating its effectiveness in AI-generated content detection. Future work will focus on refining borderline case handling and extending applicability to broader AI-generated content detection tasks, further enhancing adaptability and robustness.