Repository files navigation

This repository hosts the official website for the GraphRAG-Bench project, a comprehensive benchmark for evaluating Graph Retrieval-Augmented Generation models.

• Latest project updates and announcements
• Leaderboard activation status

• Introduces Graph Retrieval-Augmented Generation (GraphRAG) concept
• Compares traditional RAG vs GraphRAG approach
• Explains research objective: Identify scenarios where GraphRAG outperforms traditional RAG
• Visual comparison diagram of RAG vs GraphRAG

Two domain-specific leaderboards with comprehensive metrics:

1. GraphRAG-Bench (Novel)

• Evaluates models on literary/fictional content

2. GraphRAG-Bench (Medical)

• Evaluates models on medical/healthcare content

Evaluation Dimensions:

• Fact Retrieval (Accuracy, ROUGE-L)
• Complex Reasoning (Accuracy, ROUGE-L)
• Contextual Summarization (Accuracy, Coverage)
• Creative Generation (Accuracy, Factual Score, Coverage)

Four difficulty levels with representative examples:

Level 1: Fact Retrieval
Example: "Which region of France is Mont St. Michel located?"

Level 2: Complex Reasoning
Example: "How did Hinze's agreement with Felicia relate to the perception of England's rulers?"

Level 3: Contextual Summarization
Example: "What role does John Curgenven play as a Cornish boatman for visitors exploring this region?"

Level 4: Creative Generation
Example: "Retell King Arthur's comparison to John Curgenven as a newspaper article."

• Project email:GraphRAG@hotmail.com

The website is deployed via GitHub Pages:
https://graphrag-bench.github.io

├── css/                  # Stylesheets│   ├── fonts.css         # Font definitions│   ├── normalize.css     # CSS reset│   └── styles.css        # Main styles├── scripts.js            # Interactive functionality├── index.html            # Main website file└── RAGvsGraphRAG.jpg     # Comparison diagram

git clone https://github.com/GraphRAG-Bench/GraphRAG-Bench.gitcd GraphRAG-Bench# Open index.html in browser

Contributions to improve the benchmark website are welcome. Please contact the project team via email.

This repository hosts the official website for the GraphRAG-Bench project, a comprehensive benchmark for evaluating Graph Retrieval-Augmented Generation models.

• [2025-05-25] Leaderboard is on!

• Introduces Graph Retrieval-Augmented Generation (GraphRAG) concept
• Compares traditional RAG vs GraphRAG approach
• Explains research objective: Identify scenarios where GraphRAG outperforms traditional RAG
• Visual comparison diagram of RAG vs GraphRAG

Two domain-specific leaderboards with comprehensive metrics:

1. GraphRAG-Bench (Novel)

• Evaluates models on literary/fictional content

2. GraphRAG-Bench (Medical)

• Evaluates models on medical/healthcare content

Evaluation Dimensions:

• Fact Retrieval (Accuracy, ROUGE-L)
• Complex Reasoning (Accuracy, ROUGE-L)
• Contextual Summarization (Accuracy, Coverage)
• Creative Generation (Accuracy, Factual Score, Coverage)

Four difficulty levels with representative examples:

Level 1: Fact Retrieval
Example: "Which region of France is Mont St. Michel located?"

Level 2: Complex Reasoning
Example: "How did Hinze's agreement with Felicia relate to the perception of England's rulers?"

Level 3: Contextual Summarization
Example: "What role does John Curgenven play as a Cornish boatman for visitors exploring this region?"

Level 4: Creative Generation
Example: "Retell King Arthur's comparison to John Curgenven as a newspaper article."

• Project email:GraphRAG@hotmail.com

The website is deployed via GitHub Pages:
https://graphrag-bench.github.io

├── css/                  # Stylesheets│   ├── fonts.css         # Font definitions│   ├── normalize.css     # CSS reset│   └── styles.css        # Main styles├── scripts.js            # Interactive functionality├── index.html            # Main website file└── RAGvsGraphRAG.jpg     # Comparison diagram

git clone https://github.com/GraphRAG-Bench/GraphRAG-Bench.gitcd GraphRAG-Benchmark# Open index.html in browser

Contributions to improve the benchmark website are welcome. Please contact the project team via email.