Background
This game is based on the research paper "Unifying Large Language Models and Knowledge Graphs".
Key Concepts
- LLMs (Large Language Models): AI models like ChatGPT that generate text but may lack factual accuracy
- Knowledge Graphs: Structured databases containing verified facts and relationships
- The Challenge: LLMs need access to factual knowledge, while KGs need natural language capabilities
Game Mechanics
- Blue nodes represent LLM queries or capabilities
- Green nodes represent Knowledge Graph facts
- Draw bridges between compatible nodes to create unified AI systems
- Correct connections earn points and unlock new challenges
- Wrong connections reduce accuracy - be careful!
Scoring
- Correct bridge: +100 points
- Speed bonus: Extra points for quick connections
- Perfect level: 2x multiplier for 100% accuracy