Table of contents<\/h3>\n\n\n\n\n- My data, my rules: Data protection and transparency in the use of LLMs<\/li>\n\n\n\n
- Specific information for specific questions – Retrieval Augmentation Generation (RAG)\n
\n- 1) Fine tuning<\/li>\n\n\n\n
- 2) Retrieval Augmented Generation<\/li>\n<\/ul>\n<\/li>\n\n\n\n
- Evaluation of RAG systems<\/li>\n\n\n\n
- Outlook & conclusion<\/li>\n\n\n\n
- References<\/li>\n\n\n\n
- Read more<\/li>\n\n\n\n
- Authors<\/li>\n<\/ul>\n<\/div>
![\"\"](\"https:\/\/risc.web-email.at\/app\/uploads\/2024\/09\/cstaub_Visualization_of_a_language_model_security_internal_co_d438bb2f-f2de-40a1-8cff-031f52e1b5a2_2-1-1.png\")
<\/figure><\/div>\n\n<\/div>\n\nThe rapid advances in AI have now also significantly improved the quality of publicly available model alternatives. Companies can now also use powerful models securely and specifically with company-owned data in a specially selected infrastructure. These new possibilities also ensure transparent and trustworthy use that prioritizes the protection of sensitive information. In this article, you can find out how this is possible at a technical level and what is important. <\/p>\n
\n\nMy data, my rules: Data protection and transparency in the use of LLMs<\/h3>\n\n\n\n
In general, a distinction can be made between open-source and closed-source models. As the name suggests, closed-source LLMs are models in which the implementation details are not publicly accessible. This has the direct consequence that it is not clearly traceable whether and how the queries and model responses entered are further used by LLM providers. However, the advantage of closed-source applications is that business processes can be improved quickly with little to no development effort. <\/p>\n\n\n\n
In contrast, open source models such as those from Mistral AI<\/a> offer far more transparency. Essential model information can be viewed and is therefore easier to understand. With information on the architecture and model weights (in which the learned knowledge is encoded), the model can also be further developed (trained) with company-specific data. This allows its performance to be improved for a specific use case, language or domain. The use of open source models offers many advantages in this respect, but this goes hand in hand with increased effort and the necessary technical expertise. Such models often have to be hosted in a special infrastructure with sufficient computing resources and the support effort is significantly higher. <\/p>\n\n\n\nThe following table shows a comparison of selected functions:<\/p>\n\n\n\n
- \n
- 1) Fine tuning<\/li>\n\n\n\n
- 2) Retrieval Augmented Generation<\/li>\n<\/ul>\n<\/li>\n\n\n\n
- Evaluation of RAG systems<\/li>\n\n\n\n
- Outlook & conclusion<\/li>\n\n\n\n
- References<\/li>\n\n\n\n
- Read more<\/li>\n\n\n\n
- Authors<\/li>\n<\/ul>\n<\/div><\/figure><\/div>\n\n<\/div>\n\n
The rapid advances in AI have now also significantly improved the quality of publicly available model alternatives. Companies can now also use powerful models securely and specifically with company-owned data in a specially selected infrastructure. These new possibilities also ensure transparent and trustworthy use that prioritizes the protection of sensitive information. In this article, you can find out how this is possible at a technical level and what is important. <\/p>\n
\n\nMy data, my rules: Data protection and transparency in the use of LLMs<\/h3>\n\n\n\n
In general, a distinction can be made between open-source and closed-source models. As the name suggests, closed-source LLMs are models in which the implementation details are not publicly accessible. This has the direct consequence that it is not clearly traceable whether and how the queries and model responses entered are further used by LLM providers. However, the advantage of closed-source applications is that business processes can be improved quickly with little to no development effort. <\/p>\n\n\n\n
In contrast, open source models such as those from Mistral AI<\/a> offer far more transparency. Essential model information can be viewed and is therefore easier to understand. With information on the architecture and model weights (in which the learned knowledge is encoded), the model can also be further developed (trained) with company-specific data. This allows its performance to be improved for a specific use case, language or domain. The use of open source models offers many advantages in this respect, but this goes hand in hand with increased effort and the necessary technical expertise. Such models often have to be hosted in a special infrastructure with sufficient computing resources and the support effort is significantly higher. <\/p>\n\n\n\n
The following table shows a comparison of selected functions:<\/p>\n\n\n\n
![\"\"](\"https:\/\/risc.web-email.at\/app\/uploads\/2024\/09\/Indexing-1024x724.jpg\")