Large Language Models
142 views
Grounding LLM
Quick Definition
Connecting LLM outputs to verifiable external sources
Full Definition
Connecting LLM outputs to verifiable external sources for factual accuracy.
Examples
RAG, citation systems, fact verification
Related Terms
retrieval-augmented-generation
hallucination
More Large Language Models Terms
Flash Attention
Memory-efficient attention using GPU SRAM block computation
Semantic Search
Search technique understanding meaning rather than keywords
RLHF
Aligning LLMs with human preferences using reinforcement learning
Scaling Laws
Relationships between model size, data, compute, and performance
Next Token Prediction
Core LLM objective predicting the next token from context
Quantization LLM
Reducing LLM weight precision for efficient inference