Skip to main content
Go to the home page of the European Commission (opens in new window)
English en
CORDIS - EU research results
CORDIS

PersonalAI: Efficient and Private Text Personalization with Large Language Models

Project description

Developing private personalisation of open-source LLMs

The rise of large language models (LLMs) creates a conflict between functionality and privacy, as users must share sensitive data with third parties. A PanzaMail study found that fine-tuning models on 50 to 100 emails can mimic a user’s writing style, while the RoSA method enables personalisations with over 90 % less computational power. The ERC-funded PersonalAI project will develop private, on-device personalisation of open-source LLMs. It features a system that manages query complexity, processes simple tasks locally, sanitises sensitive data, and re-personalises outputs. Targeting the EU AI market, it will ensure data privacy and GDPR compliance while allowing users to maintain ownership of their data and access advanced text-generation capabilities.

Objective

The rapid adoption of Large Language Models (LLMs) for text generation has created a critical tension between functionality and privacy: while users increasingly rely on services like ChatGPT for personal and business communications, such cloud-based systems require surrendering control of sensitive data to third-party companies, often outside EU jurisdiction. The PersonalAI project addresses this fundamental challenge by enabling fully private, on-device personalization of open-source LLMs, leveraging breakthrough compression and fine-tuning techniques developed in the PI's ERC Starting Grant ScaleML project. Our preliminary PanzaMail study showed that models fine-tuned on as few as 50-100 user emails can generate text closely following genuine user writing, while our novel RoSA method enables this personalization on commodity hardware—reducing computational requirements by over 90% compared to standard approaches.

The technical innovation of the PersonalAI proof-of-concept lies in a four-component system that triages queries by complexity, executes simple tasks locally with efficiently-trained personalized models, sanitizes sensitive information from complex queries before cloud processing, and re-personalizes external outputs to match user style. As such, PersonalAI targets the rapidly-expanding EU AI market, where data sovereignty and GDPR compliance are paramount, for both companies and individual users. It offers the first solution that combines the personalization quality of proprietary services with complete data privacy. The project assembles a world-class team including the PI, lead developer Eugenia Iofinova (architect of PanzaMail), and two MIT advisors with deep entrepreneurial expertise. By transforming academic breakthroughs into a commercially viable product, PersonalAI will establish a new paradigm where users maintain complete ownership of their data and AI models while accessing state-of-the-art text generation and model editing capabilities.

Fields of science (EuroSciVoc)

Programme(s)

Topic(s)

Funding Scheme

HORIZON-ERC-POC - HORIZON ERC Proof of Concept Grants

See all projects funded under this funding scheme

Call for proposal

(opens in new window) ERC-2025-POC

See all projects funded under this call

Host institution

INSTITUTE OF SCIENCE AND TECHNOLOGY AUSTRIA
Net EU contribution
€ 150 000,00
Address
Am Campus 1
3400 Klosterneuburg
Austria
Region
Ostösterreich Niederösterreich Wiener Umland/Nordteil
Activity type
Higher or Secondary Education Establishments
Links
Total cost
No data

Beneficiaries (1)