The automated extraction of data from scientific charts is a critical task for large-scale literature analysis. While multimodal Large Language Models (LLMs) show promise, their accuracy on non-standardized charts remains a challenge. This raises a key research question: what is the most effective strategy to improve model performance (high-level semantic priming) or low-level spatial priming? This paper presents a comparative investigation into these two distinct strategies. We describe our exploratory experiments with semantic methods, such as a two-stage metadata-first framework and Chain-of-Thought, which failed to produce a statistically significant improvement. In contrast, we present a simple but highly effective spatial priming method: overlaying a coordinate grid onto the chart image before analysis. Our quantitative experiment on a synthetic dataset demonstrates that this grid-based approach provides a statistically significant reduction in data extraction error (SMAPE reduced from 25.5% to 19.5%, p < 0.05) compared to a baseline. We conclude that for the current generation of multimodal models, providing explicit spatial context is a more effective and reliable strategy than high-level semantic guidance for this class of tasks.

翻译：从科学图表中自动提取数据是大规模文献分析的关键任务。尽管多模态大语言模型（LLMs）展现出潜力，但它们在处理非标准化图表时的精度仍面临挑战。这引发了一个核心研究问题：哪种策略能更有效提升模型性能——高层语义先验还是低层空间先验？本文针对这两种策略进行了比较性研究。我们描述了语义方法（如两阶段元数据优先框架和思维链）的探索性实验，这些方法未能产生统计显著的改进。相比之下，我们提出了一种简单而高效的空间先验方法：在分析前在图表图像上叠加坐标网格。基于合成数据集的定量实验表明，与基线相比，这种基于网格的方法显著降低了数据提取误差（SMAPE从25.5%降至19.5%，p < 0.05）。我们的结论是：对于当前代的多模态模型，在图表数据提取任务中，提供显式空间上下文比高层语义引导更有效且更可靠。