Personalized Graph-Empowered Large Language Model for Proactive Information Access

2026-02-25

AI Summary

This work addresses the limitations of existing memory-augmented systems, which struggle to effectively support users in recalling ambiguous or forgotten life events due to data scarcity and insufficient model adaptability. To overcome these challenges, the authors propose a flexible framework that integrates large language models with personalized knowledge graphs. The architecture features a swappable foundation model and an adjustable fact-retrieval mechanism, enabling rapid adaptation to newly added log data. Furthermore, it incorporates an active information access decision module that dynamically identifies users’ latent recall needs. Experimental results demonstrate that the proposed approach significantly enhances recall efficiency and accurately reconstructs users’ past experiences, thereby validating the effectiveness and feasibility of graph-augmented large language models for personalized memory assistance.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

Since individuals may struggle to recall all life details and often confuse events, establishing a system to assist users in recalling forgotten experiences is essential. While numerous studies have proposed memory recall systems, these primarily rely on deep learning techniques that require extensive training and often face data scarcity due to the limited availability of personal lifelogs. As lifelogs grow over time, systems must also adapt quickly to newly accumulated data. Recently, large language models (LLMs) have demonstrated remarkable capabilities across various tasks, making them promising for personalized applications. In this work, we present a framework that leverages LLMs for proactive information access, integrating personal knowledge graphs to enhance the detection of access needs through a refined decision-making process. Our framework offers high flexibility, enabling the replacement of base models and the modification of fact retrieval methods for continuous improvement. Experimental results demonstrate that our approach effectively identifies forgotten events, supporting users in recalling past experiences more efficiently.

Problem

• personalized memory recall
• proactive information access
• life logging
• forgotten events
• personal knowledge

Innovation

• Personalized LLM
• Knowledge Graph
• Proactive Information Access
• Memory Recall
• Lifelog Adaptation