🧪 RGB Evaluation Interface
Model and Dataset Configuration
Model Name
Dataset
API Configuration
API Key
API URL
https://api.groq.com/openai/v1/chat/completions
Evaluation Parameters
Temperature
↺
0
1.5
Noise Rate
↺
0
1
Max Instances to Evaluate
↺
1
300
Correct Passage Rate
↺
0
1
Number of Passages
↺
0
10
Enable Fact Checking
Run Evaluation Scripts
🚀 Run (evalue.py) - Noise Accuracy
🚀 Run (reject_evalue.py) - Reject Rate
🚀 Run (evalue.py) - Information Integration
🚀 Run (fact_evalue.py) - Counterfactual Checking
Output
Output