Large Language Models
263 views
Reward Model
Quick Definition
Model scoring LLM outputs based on human preferences
Full Definition
A model trained to score LLM outputs based on human preference data for RLHF training pipelines.
Examples
RLHF pipeline, preference ranking, reward shaping
Related Terms
rlhf
reward-modeling
ai-alignment
More Large Language Models Terms
Inference LLM
Using a trained LLM to generate outputs from inputs
RoPE
Position encoding using rotation matrices for relative positions
Prompt Caching
Storing key-value states for repeated prompt prefixes
Autoregressive Model
Generative model predicting next token from previous tokens
Synthetic Data Generation
Using AI to create artificial training data replicating patterns
Tree-of-Thought
Framework exploring multiple reasoning paths for optimal solutions