Safely and effectively integrate LLMs into your software products
Generative AI is on the rise, with large language models (LLMs) leading the way. These technologies offer innovative possibilities for implementing existing functionalities, such as natural language processing (NLP) tasks like entity extraction, sentiment analysis, and summarisation. Additionally, they enable the creation of entirely new user experiences, such as chat-based interfaces and agents. It is anticipated that many software developers will equip their products with LLMs in the coming years.
While building a proof of concept with LLMs is relatively straightforward thanks to supportive technologies such as Langchain, Ollama, or Crew.ai, deploying these systems in a secure, robust, and cost-effective manner is far from trivial. How do you unit test an application where a crucial component (the LLM) behaves non-deterministically? Or how do you ensure that the outputs of your system are permissible at all times?
Introducing the LISA Research Project
In response to these challenges, Sirris and DistriNet Research Unit at KU Leuven have initiated the collective research project LISA (LLM Implementation, Security & Adaptation). LISA aims to consolidate knowledge on integrating LLMs into existing or new digital applications. The project targets Flemish software companies (SMEs) that develop and operate digital products. The focus of the research is on ensuring robustness, cybersecurity, performance, cost-efficiency, and regulatory compliance when integrating LLMs into proprietary software.
The project is expected to start on 1 January 2025, and will run for two years. Throughout this period, the accumulated knowledge will be continuously shared with the advisory group.
Why join the advisory group?
For companies that have already experimented with LLMs in a proof-of-concept format, as well as those that have not yet matched user needs with this technology, participating in the LISA project offers a time-efficient way to stay informed about this critical evolution in digital product development. Participating companies will closely follow the project and provide input on challenges (use cases) related to this theme. Sirris and DistriNet will address these challenges during the project.
Additionally, the advisory group will serve as a sounding board for monitoring project progress and reporting, composition and practical operations, intellectual property (IPR), and ethical aspects (confidentiality, use of project results, etc.), and the eventual valorisation of project outcomes.
Join LISA
Don't miss this opportunity to be part of a pioneering project that will shape the future of digital product development. Join the advisory group and collaborate with leading experts to integrate LLMs into your software products safely and effectively.
For more information or to sign up for the LISA project, contact project coordinator Nick Boucart via email, or schedule a exploratory intake meeting.
