Overlaying a grid on charts cuts LLM extraction error (SMAPE from 25.5% to 19.5%, p<0.05) and outperforms semantic priming on synthetic data.
Histograms of oriented gradients for human detection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Spatial Priming Outperforms Semantic Prompting: A Grid-Based Approach to Improving LLM Accuracy on Chart Data Extraction
Overlaying a grid on charts cuts LLM extraction error (SMAPE from 25.5% to 19.5%, p<0.05) and outperforms semantic priming on synthetic data.