ManySpace
English Giriş yap Kayıt ol

Yapay ZekâÖnerilenAIML-EVAL-014

LLM-as-a-Judge

Using models to grade model outputs, and measuring the judge's agreement with humans and its biases.

Bu konunun henüz Türkçe çevirisi yok, bu yüzden İngilizce gösteriliyor.

Zorluk
3 / 5
Önem
4 / 5
Çalışma süresi
1–2 sa
Çalışma türü
Karma

Neden önemli

The learner can measure agreement between an LLM judge and human labels and name two judge biases such as position and verbosity.

Bu konuya giden rota

Rota AIML-EVAL-014
What Is a Model? Learning from Data Tasks: Regression, Classification, and Beyond Features and Targets Datasets and Splits Classification Framing Linear Regression I: Prediction and Residuals Tokens and Tokenization Train, Validation, and Test Errors Scores and Logits Loss and Fitting: Squared Error Offline Evaluation Multiclass Scores and Softmax Autoregression Objective Functions and Empirical Risk Human Evaluation Next-Token Prediction Gradient Descent in Machine Learning Likelihood Generation Metrics Stochastic and Mini-batch Optimization Cross-Entropy Loss The Language-Modeling Objective Pretraining LLM Evaluation LLM-as-a-Judge