Narrative visualization effectively transforms data into engaging stories, making complex information accessible to a broad audience. Large models, essential for narrative visualization, inherently facilitate this process through their superior ability to handle natural language queries and answers, generate cohesive narratives, and enhance visual communication. Inspired by previous work in narrative visualization and recent advances in large models, we synthesized potential tasks and opportunities for large models at various stages of narrative visualization. In our study, we surveyed 79 papers to explore the role of large models in automating narrative visualization creation. We propose a comprehensive pipeline that leverages large models for crafting narrative visualization, categorizing the reviewed literature into four essential phases: Data, Narration, Visualization, and Presentation. Additionally, we identify nine specific tasks where large models are applied across these stages. This study maps out the landscape of challenges and opportunities in the LM4NV process, providing insightful directions for future research and valuable guidance for scholars in the field.

翻译：叙事可视化能够将数据有效转化为引人入胜的故事，使复杂信息便于广泛受众理解。大模型作为叙事可视化的核心要素，凭借其在自然语言问答、连贯叙事生成及视觉传达增强等方面的卓越能力，天然地促进了这一过程。受先前叙事可视化研究及大模型近期进展的启发，本文综合梳理了大模型在叙事可视化各阶段中的潜在任务与机遇。我们通过调查79篇论文，深入探讨了大模型在自动化叙事可视化创作中的角色。研究提出了一套利用大模型构建叙事可视化的完整流程，并将相关文献归纳为四个核心阶段：数据、叙事、可视化和呈现。此外，我们识别出大模型在这四个阶段中应用的九项具体任务。本研究刻画了LM4NV流程中的挑战与机遇全景，为未来研究指明了富有洞察力的方向，并为该领域学者提供了有价值的指导。