Glossary

Knowledge Cutoff

What is Knowledge Cutoff?

The knowledge cutoff is the point in time up to which a language model's training data extend. The model has no inherent knowledge of events, prices, laws or products that emerged afterwards and may give outdated information unless it is supplied with current data. This can be addressed by methods that bring in your own documents or current web content at run time.

How KI.ordo helps

KI.ordo agents compensate for the cutoff by using your stored knowledge and retrieving current public pages with the “Read web page” tool.

Learn more →

Topics

LLM
Up-to-dateness
Basics

Try KI.ordo

Agents, flows and templates in one workspace – free 24-hour demo.

Start demo

← All terms

Related terms

Large language model (LLM)

A large language model (LLM) is a neural network trained on very large amounts of text, enabling it to understand and generate language. It works by calculating the most likely next token, step by step. LLMs write, summarise, translate, answer questions and generate code; well-known examples include Claude, GPT, Gemini and Llama. Without access to current sources, they only know what was in their training data.

Language models
Generative AI
+1

Hallucination

A hallucination is output from an AI model that sounds convincing but is wrong or entirely made up – such as a non-existent court ruling, an incorrect figure or an invented source. The cause: language models produce likely wording; they do not automatically look up facts. The risk falls when answers are based on verified sources, evidence is cited and people check important results.

Language models
Reliability
+1

Template

Retrieval-augmented generation (RAG)

Retrieval-augmented generation combines search with text generation: before answering, the system searches a knowledge collection – such as manuals, policies or FAQs – for relevant passages and passes them to the language model as context. The answer is therefore based on current, company-specific content rather than only on the model's training knowledge. This reduces invented statements, makes sources traceable and allows updates without retraining.

RAG
knowledge search
+1

Training Data

Training data are the examples from which an AI model learns patterns: large text collections for language models, labelled images for image models. Their quality, diversity and recency largely determine how reliable and fair a model is and how up to date its knowledge will be. For organisations it also matters whether a provider uses the customer data they enter for further training.

Data
Training
+1