Eval Definition
No OpenAI Reference
Evaluates whether the response contains references to OpenAI, its models (like ChatGPT, GPT-3, GPT-4), or identifies itself as an OpenAI product
This evaluation template checks whether a text contains references to OpenAI, its models (like ChatGPT, GPT-3, GPT-4), or identifies itself as an OpenAI product. It’s particularly useful for ensuring AI responses maintain proper branding and attribution.
Interface Usage
Python SDK Usage
Example Output
Troubleshooting
If you encounter issues with this evaluation:
- This evaluation detects both explicit mentions (“OpenAI”, “ChatGPT”) and implicit self-identification (“As an AI language model…”)
- It covers references to OpenAI as a company, its products, and its models
- If your content legitimately needs to discuss OpenAI as a subject matter, consider using a different evaluation
- For comprehensive brand compliance, combine with other brand-specific evaluations
Related Evaluations
- regex: Can be used to create custom pattern matching for specific brand-related terms
- contains-evals: Checks for the presence of specific content or phrases in text
Previous
OverviewThe Knowledge Base (KB) is the foundation for grounded, context-aware synthetic data generation and accurate evaluations. It ensures that every output whether it's data generation or evaluation is informed by your uploaded content, which is semantically processed and abstracted to reflect your organization’s unique domain.
Next