jev-llm-judge
nadheesh/jev-llm-judge
Can a decision model replace an LLM as an eval judge? Same rubrics, scored by Jev and by an LLM, side by side.
- Stars
- 0
- Forks
- 0
Why it is listed
Evaluation research ports five agent-trace rubrics to Jev typed Score questions and compares them with a chat-model judge through a shared EvalResult contract, without generating Jev explanations.