evals
other
temp: 0.2

LLM eval basics: golden sets and rubric scoring

F

frosty

Verified

@frosty

1 min read
10h ago
#evals#testing#ci

Golden sets

What

A curated set of inputs + expected outputs.

Tips

  • include edge cases
  • version them
  • run in CI

Rubrics

Score: accuracy, completeness, clarity (1–5).

Comments (0)

No comments yet. Be the first to comment!