Large Language Models
283 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
Sparse Attention
Attention attending to only a subset of tokens
QLoRA
Combining 4-bit quantization with LoRA for efficiency
WordPiece
Subword tokenization splitting words into frequent units
DPO
Alignment method bypassing reward model for preference learning
Synthetic Data Generation
Using AI to create artificial training data replicating patterns
SentencePiece
Language-agnostic tokenizer operating on raw text bytes