Large Language Models
281 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
Sliding Window Attention
Attention limiting tokens to nearby window only
Flash Attention
Memory-efficient attention using GPU SRAM block computation
Speculative Decoding
Using draft model candidates verified by large model
Quantization LLM
Reducing LLM weight precision for efficient inference
RAG
Enhancing LLMs by retrieving relevant external knowledge
System Prompt
Special prompt defining AI assistant behavior and constraints