BigHugger
sk Skill · hparreao

g-eval-workflow

Design evidence-based G-Eval or LLM-as-a-judge workflows for LLM and RAG outputs. Use when defining evaluator steps, critical dimensions, judge inputs, calibration samples, or reviewer-owned decision policies.

installs 8w
0
30-day movement
starts with the next reading
Related entries
1
Connections
0
Python
Host repository
hparreao/Awesome-AI-Evaluation-Guide
Host stars
18
Host language
Python