What is a large language model (LLM)?

At a glance

• LLM stands for Large Language Model.
• LLMs use learned patterns to calculate which word is most likely to come next.
• Multimodal LLMs process not only text but also images, audio, or documents.
• In business intelligence, LLMs explain numbers but do not calculate them reliably. KPIs should come from the BI system.
• DeltaMaster and DeltaApp include LLM-based features for chat, voice control, root cause analysis, and executive summaries.

Large language models: definition and classification

LLM stands for Large Language Model and roughly translates into German as “large language model.” It describes a neural network that statistically models language and can therefore understand and generate text.

“Large” refers to two dimensions: the amount of training data and the number of parameters, which for current models is in the billions.

LLMs are a form of generative AI and are based on deep learning. They are the technology behind well-known AI assistants and many AI features in business software.

How do large language models work?

An LLM predicts step by step which piece of text is most likely to come next. This simple task gives rise to capabilities such as summarization, translation, and question answering when combined with enormous amounts of data.

Technically, almost all current LLMs are based on the transformer architecture. At their core is the attention mechanism: For each word, the model determines which other words in the text are important for its meaning.

Important for business use: An LLM does not store a fact database; it stores probabilities. As a result, it can generate convincing but incorrect statements. These so-called hallucinations can only be mitigated through verified data sources and human oversight.

What types of LLMs are there?

LLMs differ in terms of input type, size, and deployment. For companies, it is particularly relevant whether a model can process images and whether it can be operated in their own data center.

A multimodal large language model (MLLM), for example, processes multiple types of data, such as text, images, audio, or video. It can describe a chart, extract information from a scanned invoice, or answer a question about a screenshot, for example.

What are some examples of large language models?

The best-known large language models include the GPT, Claude, Gemini, Llama, and Mistral model families. Providers release new versions at short intervals, so the table below lists only the model families.

For selecting an LLM for business use, the model name matters less than where the data is processed, which contracts apply, and how well the model fits into existing systems.

What do companies need large language models for?

Many companies use LLMs to make knowledge from data and documents available more quickly. In controlling and business intelligence, LLMs primarily shorten the path from a number to an explanation.

Typical tasks in controlling include:

• Commenting on reports: The LLM turns identified variances into an understandable management comment.
• Asking questions in natural language: Business users can ask, “Why is revenue in the South below plan?” instead of setting filters.
• Unlocking unstructured data: The LLM analyzes meeting transcripts, support tickets, or production reports and uses them to supplement the KPIs.
• Deriving recommendations for action: Based on the analysis, the LLM suggests possible actions that a human reviews and decides on.

An LLM does not replace a data warehouse or BI software. It sits above them as a language layer and is only as good as the data quality underneath.

What does Large Language Model Optimization mean?

Large Language Model Optimization refers to two different things: the technical adaptation of a model to a task and, in marketing, the visibility of content in AI answers.

In the technical sense, optimization is first of all meant mathematically. During training, a loss function is minimized until the model delivers the best possible predictions. More relevant for users are the ways to adapt a finished model for their own use:

Which LLM solution fits which use case?

The right solution depends on which data the LLM is meant to process and how reliable the result has to be. For KPIs, the rule is: the higher the requirement for correctness, the more closely the LLM must be bound to a verified data model.

Which errors often occur when using LLMs and how do you avoid them?

The most common errors arise when companies give an LLM tasks it was not built for, or when the data basis is missing.

Practical example: contribution margin variance in sales controlling

An industrial company notices in the monthly report: the contribution margin of the South region is 8 percent below plan. Previously, the controller would have set filters, rearranged reports, and written a management summary by hand.

With DeltaMaster, the head of sales asks directly: “Why is the contribution margin in the South region below plan?” The AI analysis performs a drill-down across product groups and customers. This gives her the result: two major customers received higher discounts, sales volume is on plan.

The LLM supplements the figures with context from the connected sales call logs. There, a competitor offer is documented that explains the discounts. From this, the AI formulates an assessment and suggests measures, for example a review of the discount scale. After review by the controller, the DeltaMaster Publisher sends the summary to management.

The division of labor is decisive: the figures come from the BI data model, the LLM explains them. This way every statement remains traceable to a KPI.

Use cases: Where are large language models used?

LLMs make knowledge from data and documents available more quickly. In controlling and business intelligence, they primarily shorten the path from the figure to the explanation.

Summary

A large language model is a language model that understands and generates text by calculating the most likely next word. In controlling, an LLM delivers value when it works on a verified data foundation and explains numbers rather than calculating them itself. Bissantz combines both in DeltaMaster: KPIs come from the BI model, while explanations and recommendations are generated by the LLM.