**Explicit Extraction and Reasoning (EER)** is a structured [[Prompt Engineering|prompting]] strategy that breaks down complex reasoning tasks into four explicit, sequential steps. Unlike [[Zero-Shot Chain-of-Thought (COT)|Zero-Shot COT]], EER guides the model through a predefined reasoning pipeline. ## Four-Step Process 1. **Extraction of Regions** - Identify relevant regions/areas for the question 2. **Extraction of Relevant Places** - Extract specific locations within those regions 3. **Extraction of Values from Legend** - Extract corresponding values from visual data 4. **Reasoning based on Extracted Values** - Use extracted values to reach final answer ## Performance Insights From the [[MAPWise Evaluating Vision-Language Models for Advanced Map Queries|MAPWise benchmark]]: - Most models performed better with [[Zero-Shot Chain-of-Thought (COT)|Zero-Shot COT]] - Exception: Gemini 1.5 Flash performed better with EER (strong instruction-following) - Smaller open-source models struggled with complex EER instructions ## Use Cases EER is particularly suited for: - Visual question answering (maps, charts) - Tasks requiring systematic data extraction - Models with strong instruction-following capabilities