Loading...
Skeleton of Thoughts(SoT)
Creates structured yet adaptable reasoning frameworks that can be filled with specific details
🎯 30-Second Overview
Pattern: Structured reasoning that creates a high-level skeleton then expands each component in parallel for efficient processing
Why: Accelerates complex response generation through parallel development while maintaining logical structure and coherence
Key Insight: Create skeleton structure → Expand points in parallel → Integrate sections → Ensure consistency → Final synthesis
⚡ Quick Implementation
📋 Do's & Don'ts
🚦 When to Use
Use When
- • Complex multi-part responses or analyses
- • When parallel processing can accelerate reasoning
- • Structured writing or presentation tasks
- • Problems with independent sub-components
- • When consistency across sections is crucial
Avoid When
- • Simple, single-concept questions
- • Highly sequential reasoning tasks
- • When parallel processing is not beneficial
- • Real-time applications requiring immediate response
- • Problems requiring deep, interconnected reasoning
📊 Key Metrics
💡 Top Use Cases
References & Further Reading
Deepen your understanding with these curated resources
Academic Papers
Skeleton-of-Thought: Large Language Models Can Do Parallel Decoding (Ning et al., 2023)
Tree of Thoughts: Deliberate Problem Solving with Large Language Models (Yao et al., 2023)
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models (Wei et al., 2022)
Parallel Context Windows for Large Language Models (Chen et al., 2023)
Contribute to this collection
Know a great resource? Submit a pull request to add it.
Skeleton of Thoughts(SoT)
Creates structured yet adaptable reasoning frameworks that can be filled with specific details
🎯 30-Second Overview
Pattern: Structured reasoning that creates a high-level skeleton then expands each component in parallel for efficient processing
Why: Accelerates complex response generation through parallel development while maintaining logical structure and coherence
Key Insight: Create skeleton structure → Expand points in parallel → Integrate sections → Ensure consistency → Final synthesis
⚡ Quick Implementation
📋 Do's & Don'ts
🚦 When to Use
Use When
- • Complex multi-part responses or analyses
- • When parallel processing can accelerate reasoning
- • Structured writing or presentation tasks
- • Problems with independent sub-components
- • When consistency across sections is crucial
Avoid When
- • Simple, single-concept questions
- • Highly sequential reasoning tasks
- • When parallel processing is not beneficial
- • Real-time applications requiring immediate response
- • Problems requiring deep, interconnected reasoning
📊 Key Metrics
💡 Top Use Cases
References & Further Reading
Deepen your understanding with these curated resources
Academic Papers
Skeleton-of-Thought: Large Language Models Can Do Parallel Decoding (Ning et al., 2023)
Tree of Thoughts: Deliberate Problem Solving with Large Language Models (Yao et al., 2023)
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models (Wei et al., 2022)
Parallel Context Windows for Large Language Models (Chen et al., 2023)
Contribute to this collection
Know a great resource? Submit a pull request to add it.