Large Language Models
128 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
Large Language Model
Massive AI model trained on text for language understanding and generation
Structured Output
Generating LLM responses in predefined machine-readable formats
Llama
Meta AI's open-source large language models
Grounded Generation
Generating outputs faithful to provided source documents
Quantization LLM
Reducing LLM weight precision for efficient inference
Adapter Layer
Small trainable modules in frozen transformer layers