LLM-as-a-Judge

○ unseen · kind concept · level 0 · 0h

• Requiere: Large Language Models

• Aplica: Model Evaluation

Using a language model to grade another model’s output; its quality depends on calibrating the judge like a human. InfoQ: “Powering the Future” (Intuit).

Enlaces

• Requiere: Large Language Models
• Aplica: Model Evaluation