Large Language Models
262 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
Fine-Tuning
Further training pre-trained models on specific domain data
Pre-training
Initial training learning general language patterns from text
Attention Head
Individual attention mechanism learning specific patterns
GGUF
File format for LLMs optimized for local inference
Alignment Tax
Performance cost of aligning AI with human preferences
Prompt Template
Reusable structured format with dynamic input placeholders