A Benchmark and Knowledge-Grounded Framework for Advanced Multimodal Personalization Study

TL;DR

This paper introduces Life-Bench, a comprehensive multimodal benchmark for personalization, and LifeGraph, a knowledge graph framework to improve reasoning, revealing significant gaps in current methods and highlighting future research directions.

Contribution

The paper presents Life-Bench, a novel benchmark for multimodal personalization, and LifeGraph, a knowledge graph framework, addressing the lack of suitable evaluation tools and structured reasoning methods.

Findings

Existing methods perform poorly on complex personalized tasks.

LifeGraph improves reasoning capabilities over structured personal data.

Significant performance headroom remains for future research.

Abstract

The powerful reasoning of modern Vision Language Models open a new frontier for advanced personalization study. However, progress in this area is critically hampered by the lack of suitable benchmarks. To address this gap, we introduce Life-Bench, a comprehensive, synthetically generated multimodal benchmark built on simulated user digital footprints. Life-Bench features over questions evaluating a wide spectrum of capabilities, from persona understanding to complex reasoning over historical data. These capabilities expand far beyond prior benchmarks, reflecting the critical demands essential for real-world applications. Furthermore, we propose LifeGraph, an end-to-end framework that organizes personal context into a knowledge graph to facilitate structured retrieval and reasoning. Our experiments on Life-Bench reveal that existing methods falter significantly on complex personalized tasks, exposing a large performance headroom, especially in relational, temporal and aggregative reasoning. While LifeGraph closes this gap by leveraging structured knowledge and demonstrates a promising direction, these advanced personalization tasks remain a critical open challenge, motivating new research in this area.