RUVA: Personalized Transparent On-Device Graph Reasoning

2026-02-17

AI Summary

This work addresses critical limitations of current personal AI systems, which rely on black-box retrieval-augmented generation and consequently suffer from poor interpretability, inability to precisely delete memorized content, susceptibility to hallucinations and privacy leaks, and failure to uphold the right to be forgotten. To overcome these issues, the authors propose a “glass-box” architecture grounded in on-device personal knowledge graphs, shifting the AI memory mechanism from vector-based matching to graph-based reasoning. This approach enables human-in-the-loop, fact-level memory management, allowing users to transparently inspect, precisely edit, trace, and definitively delete specific facts. By eliminating data “ghosts” and ensuring granular control over personal knowledge, the system empowers users with full ownership of their data and robust compliance with privacy regulations.

Technology Category

• Machine Learning: Privacy
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Humans and AI: Intelligent User Interfaces

Application Category

• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• Security and Privacy: Data transparency and provenance

Abstract

The Personal AI landscape is currently dominated by "Black Box" Retrieval-Augmented Generation. While standard vector databases offer statistical matching, they suffer from a fundamental lack of accountability: when an AI hallucinates or retrieves sensitive data, the user cannot inspect the cause nor correct the error. Worse, "deleting" a concept from a vector space is mathematically imprecise, leaving behind probabilistic "ghosts" that violate true privacy. We propose Ruva, the first "Glass Box" architecture designed for Human-in-the-Loop Memory Curation. Ruva grounds Personal AI in a Personal Knowledge Graph, enabling users to inspect what the AI knows and to perform precise redaction of specific facts. By shifting the paradigm from Vector Matching to Graph Reasoning, Ruva ensures the "Right to be Forgotten." Users are the editors of their own lives; Ruva hands them the pen. The project and the demo video are available at http://sisinf00.poliba.it/ruva/.

Problem

• Black Box AI
• Accountability
• Right to be Forgotten
• Privacy
• Hallucination

Innovation

• Graph Reasoning
• Personal Knowledge Graph
• Right to be Forgotten
• Human-in-the-Loop
• Transparent AI