Glossary · Phase 1 · Building with LLMs
Borda count
Combining several rankings by giving each item points for how many items it beats in each ranking, then adding the points up.
Try it now
A judge is a model too, so it needs its own eval.
Learn it properly
LLM-as-judge · Grade open-ended output with rubrics and a second model. About 30 minutes.
Other terms from the same lesson
- LLM-as-judge: Using one model to grade another model's answers against a rubric.
Never trained an AI?
Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account.