Inrupt & Northeastern University: AI In a World of User-Owned Data

As organizations integrate AI into their services, they must ensure that the data on which AI acts is securely processed and accurately reflects users’ intentions and preferences. When data is stored in user-centric Active Wallets, large language models (LLMs) can achieve higher levels of personalization and performance than traditional LLMs. Northeastern University and Inrupt worked together to produce a state-of-the-art platform where generative AI applications run on user-owned data. This project makes innovative solutions possible in financial services, retail, and healthcare, among other industries. 

The highly personalized LLM platform works with data stored in Inrupt’s Solid Wallet, paving the way for generative AI applications to work in the world of user-owned data. AISH experts also showed Inrupt examples of how the architecture worked, including in a natural language movie recommender.

The solution showed the potential to build highly-personalized generative AI applications in ways that preserve user control of data and privacy, for instance by ensuring user data won’t be used to train future models.

Furthermore, by using an individual’s Solid Wallet data, the LLMs have several key advantages over generic LLMs. Namely, the LLMs offer a closer fit between the model and its use cases because of its understanding of the user and clearly defined application scope.

Read the full case study here.

Interested in how Inrupt’s Active Wallet creates innovation in AI? Schedule a call with our team today. 

‍