Glossary
Self-preference bias
On this page
The short answer
Definition
Self-preference bias is a judge model’s tendency to rate outputs from its own model family more favorably. It matters most when you compare models; read the outputs yourself before choosing one.
In practice
If you compare OpenAI and Anthropic models in Litmiq, try a judge from a different family on a sample, or read the cases, before you treat the ranking as final.
Related terms
FAQ
Does Litmiq implement “Self-preference bias” as a built-in metric?
Only where the definition itself says so. Many terms are industry vocabulary. Litmiq is a single-turn, BYOK prompt tester with an LLM judge, not a full evaluation platform.
Where is the rest of the glossary?
The hub at /glossary lists every term. This page is the standalone entry for Self-preference bias.
See the term in a suite
Many glossary entries have a matching template you can run in the browser.
- Free, no signup
- Runs in your browser
- Your OpenAI key, sent only to OpenAI