The world of Artificial Intelligence (AI) really loves its abbreviations. You can’t read an article without stumbling into one.
My new abbreviation today is RAG (retrieval-augmented generation).
RAG is a framework that combines aspects of both retrieval-based and generation-based approaches in natural language processing (NLP).
If I understand it correctly you can get a model to retrieve information from a huge amount of text. You have a knowledge base that is used as the foundation of your model and when someone asks a question RAG will find the answer from that text.
Other AI abbreviations I have come across include:
ML: Machine Learning
RL: Reinforcement Learning
DL: Deep Learning
NLP: Natural Language Processing
LLM: Large language model
GPT: Generative Pre-trained Transformer
DNN: Deep Neural Network
GAN: Generative Adversarial Network
RNN: Recurrent Neural Network
LSTM: Long Short-Term Memory
LARF: Logical consistency, Accuracy, Relevance and Factual correctness. #prompt engineering
SALT: style; audience; length; and tone. #prompt engineering