Skip to main content
Your questions and your company’s knowledge, data, and documents are saved securely and will never be used to train AI models. We are GDPR compliant.

​
What Are LLMs?

Artificial Intelligence (AI) is a broad field of computer science focused on creating machines that can perform tasks that typically require human intelligence. This includes things like learning, problem-solving, and understanding language. Large Language Models (LLMs) are a specific type of AI specialised in understanding and generating language. They are trained on vast amounts of text data, which allows them to understand, generate, and interact with human language in a very sophisticated way. There are many different LLMs available, such as the GPT series from OpenAI, Google’s Gemini family of models, and open-source models like Llama. Find out more about available models via this link. In short: All LLMs are AI, but not all AI are LLMs.

​
How Genow Uses LLMs

Genow uses LLMs to provide you with precise answers based on your company’s internal knowledge. When you ask a question, Genow first searches through the relevant documents and then uses an LLM to formulate a clear and concise answer from the information (i.e. text snippets) found. For a more detailed look at how Genow finds information, please read our article on the Genow search.
Genow does not train the AI models. Your data is exclusively used to answer your questions and is not used for any training purposes.

​
How Do LLMs Work?

Generally, LLMs are statistical tools. They work by calculating the probability of what the next word in a sentence should be, based on the patterns they learned during their training.

​
Training and Capabilities

LLMs are trained on a massive dataset of text and code. During this training, they learn the relationships between words, grammar, context, and even reasoning patterns. This process allows them to:
  • Generate text,
  • Summarize long documents,
  • Translate languages &
  • Answer your questions.

​
The Statistical Component in Action

Imagine you see the sentence: “The sky is ____.” Based on the vast amount of text it has analyzed, an LLM knows that the word “blue” is statistically the most likely word to follow. It calculates the probability for all possible next words and chooses the most likely one. It’s a bit like a very powerful autocomplete function. The same logic is used for answer generation on the Genow platform. However, the LLMs use text snippets from relevant documents that are found via a semantic search.

​
The Importance of Prompting

A prompt is the instruction or question you give to the LLM. The way you formulate your prompt directly influences the quality and relevance of the answer you receive. The clearer and more specific your prompt, the better the result will be. Read our prompt-guide to find our more.