Spatial Priming Outperforms Semantic Prompting: A Grid-Based Approach to Improving LLM Accuracy on Chart Data Extraction

Computer Science > Artificial Intelligence [Submitted on 6 May 2026] Spatial Priming Outperforms Semantic Prompting: A Grid-Based Approach to Improving LLM Accuracy on Chart Data Extraction Andrei Lazarev, Dmitrii Sedov, Alexander Galkin 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. Comments: his is the version of the article accepted for publication in SUMMA 2025 after peer review. The final, published version is available at IEEE Xplore: this https URL Subjects: Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV); Software Engineering (cs.SE) Cite as: arXiv:2605.08220 [cs.AI]   (or arXiv:2605.08220v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2605.08220 Focus to learn more Journal reference: 2025 7th International Conference on Control Systems, Mathematical Modeling, Automation and Energy Efficiency (SUMMA), Lipetsk, Russian Federation, 2025, pp. 799-804 Related DOI: https://doi.org/10.1109/SUMMA68668.2025.11302248 Focus to learn more Submission history From: Andrei Lazarev [view email] [v1] Wed, 6 May 2026 13:38:29 UTC (476 KB) Access Paper: view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-05 Change to browse by: cs cs.CE cs.CL cs.CV cs.SE References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)