RAG does: retrieves relevant documents before generating to reduce hallucination

RAG reduces AI hallucinations

RAG integrates real-time information retrieval with LLMs, enhancing accuracy and reducing errors.

RAG pulls relevant text from various sources before generating responses, ensuring that the information is up-to-date and accurate.

This method helps LLMs stick to the facts, avoiding the creation of false or misleading information.

Example

A chatbot using RAG can access the latest company policies and provide accurate responses instead of inventing nonexistent ones.

Remember this

Reducing AI hallucinations is crucial for maintaining trust and reliability in AI-generated content.

Text adapted from Wikipedia, licensed under CC BY-SA 4.0.

Related concepts

Retrieval-augmented generation

RAG enables LLMs to access new information without retraining

paged attention (vLLM) improves serving throughput

Paged attention (vLLM) improves serving throughput by reducing latency through non-contiguous KV-cache pages, enabling faster data retrieval

Masking (behavior)

Can you not see what's right in front of you?

dropout works as regularization: it approximates an ensemble of subnetworks

Why does turning off neurons randomly help a brainy computer learn better?

Adam has bias correction: divides by (1-β^t) in early steps

Why do we sometimes need to fix mistakes in computer decisions?

GQA reduces KV-cache memory by the group factor

Ever wondered how websites stay fresh in search results?

Swipe through 100 ML concepts daily