ManySpace
Türkçe Sign in Sign up

AI & MLRecommendedAIML-LM-023

Reward Models from Human Preferences

Learning a scalar score from pairwise human comparisons with a Bradley-Terry loss.

Difficulty
3 / 5
Importance
4 / 5
Study time
1–2 h
Kind of work
Mixed

Why it matters

The learner can compute the Bradley-Terry probability for a preference pair and explain what the reward model can and cannot capture.

The route to this topic

Route AIML-LM-023
What Is a Model? Tasks: Regression, Classification, and Beyond Features and Targets Classification Framing Linear Regression I: Prediction and Residuals Embeddings Tokens and Tokenization Scores and Logits Loss and Fitting: Squared Error Sigmoid and Probabilities Multiclass Scores and Softmax The Artificial Neuron Autoregression Objective Functions and Empirical Risk Logistic Regression Activation Functions Next-Token Prediction Gradient Descent in Machine Learning Likelihood The Multilayer Perceptron Binary Cross-Entropy Cross-Entropy Loss Stochastic and Mini-batch Optimization Transfer Learning The Language-Modeling Objective Fine-Tuning Pretraining Supervised Fine-Tuning Preference Optimization Reward Models from Human Preferences