adesso BLOG

Large Language Models (LLMs), above all ChatGPT, have taken all areas of computer science by storm over the past year. As they are trained on a broad database, LLMs are fundamentally application-agnostic. Despite their extensive knowledge, however, they have gaps, particularly in highly specialised applications, which in the worst case can only appear to be compensated for by hallucinations. To reduce this risk, "Retrieval Augmented Generation" (RAG) has been established.

The world of artificial intelligence is developing at a breathtaking speed, and large language models (LLMs) are at the forefront of this revolution. LLM operationalisation is an essential part of this development and offers companies the opportunity not only to push the boundaries of technology, but also to set new standards for human–machine interaction. We explain why this is the case in our blog post.

In the world of artificial intelligence (AI), it has often been assumed that larger models are better. However, recent research shows that smaller language models, which were previously considered to only be an intermediate step on the path towards larger models, outperform or at least match the performance of large language models (LLMs) in various applications. In my blog post, I explore this point and present a variety of small language models. I will also take a look at the pros and cons of SLMs in a direct comparison with LLMs.

Running large language models using a fancy, ready-to-use interface increases accessibility for many, even for people who do not know any programming languages. Part two of my blog series focuses on technical aspects such as specifying the scope of the summary, prompt engineering and quality factors.

What does open source mean, and why are open source language models actually so important? In my blog post, I will answer these questions and introduce you to three important open source large language models in more detail.

In this blog post, I want to give an introduction to the AI models of the German company Aleph Alpha given the current attention that large language models such as OpenAI’s ChatGPT are attracting and how people are increasingly using it to solve natural language processing problems. I will explain why it is of great importance to have AI companies based in Europe and why the everyday use of ChatGPT can be problematic given that it is the product of a US company.

In this blog post, I will show how you can harness the power of Aleph Alpha’s ‘Luminous’ series of large language models for automated document processing. I will present detailed use cases and explain how Luminous efficiently, accurately and cost-effectively enables the extraction of information from documents.