I2CR: Intra- and Inter-modal Collaborative Reflections for Multimodal Entity Linking

TL;DR

This paper introduces I2CR, a novel multimodal entity linking framework that emphasizes iterative reasoning over visual clues to improve accuracy, outperforming existing methods on multiple datasets.

Contribution

The paper presents a new LLM-based framework that uses intra- and inter-modal reflections with multi-round reasoning, addressing limitations of previous one-time visual feature extraction methods.

Findings

Outperforms state-of-the-art methods on three datasets

Achieves 3.2%, 5.1%, and 1.6% improvements respectively

Demonstrates effectiveness of iterative visual reasoning in multimodal linking

Abstract

Multimodal entity linking plays a crucial role in a wide range of applications. Recent advances in large language model-based methods have become the dominant paradigm for this task, effectively leveraging both textual and visual modalities to enhance performance. Despite their success, these methods still face two challenges, including unnecessary incorporation of image data in certain scenarios and the reliance only on a one-time extraction of visual features, which can undermine their effectiveness and accuracy. To address these challenges, we propose a novel LLM-based framework for the multimodal entity linking task, called Intra- and Inter-modal Collaborative Reflections. This framework prioritizes leveraging text information to address the task. When text alone is insufficient to link the correct entity through intra- and inter-modality evaluations, it employs a multi-round iterative strategy that integrates key visual clues from various aspects of the image to support reasoning and enhance matching accuracy. Extensive experiments on three widely used public datasets demonstrate that our framework consistently outperforms current state-of-the-art methods in the task, achieving improvements of 3.2%, 5.1%, and 1.6%, respectively. Our code is available at https://github.com/ziyan-xiaoyu/I2CR/.