Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhou, Mo, Wang, Jianwei, Wang, Kai, Paik, Helen, Zhang, Ying, Zhang, Wenjie
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2604.20283
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910156974981120
author Zhou, Mo
Wang, Jianwei
Wang, Kai
Paik, Helen
Zhang, Ying
Zhang, Wenjie
author_facet Zhou, Mo
Wang, Jianwei
Wang, Kai
Paik, Helen
Zhang, Ying
Zhang, Wenjie
contents Multimodal Entity Linking (MEL) is a fundamental task in data management that maps ambiguous mentions with diverse modalities to the multimodal entities in a knowledge base. However, most existing MEL approaches primarily focus on optimizing instance-centric features and evidence, leaving broader forms of evidence and their intricate interdependencies insufficiently explored. Motivated by the observation that human expert decision-making process relies on multi-perspective judgment, in this work, we propose MSR-MEL, a Multi-perspective Evidence Synthesis and Reasoning framework with Large Language Models (LLMs) for unsupervised MEL. Specifically, we adopt a two-stage framework: (1) Offline Multi-Perspective Evidence Synthesis constructs a comprehensive set of evidence. This includes instance-centric evidence capturing the instance-centric multimodal information of mentions and entities, group-level evidence that aggregates neighborhood information, lexical evidence based on string overlap ratio, and statistical evidence based on simple summary statistics. A core contribution of our framework is the synthesis of group-level evidence, which effectively aggregates vital neighborhood information by graph. We first construct LLM-enhanced contextualized graphs. Subsequently, different modalities are jointly aligned through an asymmetric teacher-student graph neural network. (2) Online Multi-Perspective Evidence Reasoning leverages the power of LLM as a reasoning module to analyze the correlation and semantics of the multi-perspective evidence to induce an effective ranking strategy for accurate entity linking without supervision. Extensive experiments on widely used MEL benchmarks demonstrate that MSR-MEL consistently outperforms state-of-the-art unsupervised methods. The source code of this paper was available at: https://anonymous.4open.science/r/MSR-MEL-C21E/.
format Preprint
id arxiv_https___arxiv_org_abs_2604_20283
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Multi-Perspective Evidence Synthesis and Reasoning for Unsupervised Multimodal Entity Linking
Zhou, Mo
Wang, Jianwei
Wang, Kai
Paik, Helen
Zhang, Ying
Zhang, Wenjie
Computation and Language
Multimodal Entity Linking (MEL) is a fundamental task in data management that maps ambiguous mentions with diverse modalities to the multimodal entities in a knowledge base. However, most existing MEL approaches primarily focus on optimizing instance-centric features and evidence, leaving broader forms of evidence and their intricate interdependencies insufficiently explored. Motivated by the observation that human expert decision-making process relies on multi-perspective judgment, in this work, we propose MSR-MEL, a Multi-perspective Evidence Synthesis and Reasoning framework with Large Language Models (LLMs) for unsupervised MEL. Specifically, we adopt a two-stage framework: (1) Offline Multi-Perspective Evidence Synthesis constructs a comprehensive set of evidence. This includes instance-centric evidence capturing the instance-centric multimodal information of mentions and entities, group-level evidence that aggregates neighborhood information, lexical evidence based on string overlap ratio, and statistical evidence based on simple summary statistics. A core contribution of our framework is the synthesis of group-level evidence, which effectively aggregates vital neighborhood information by graph. We first construct LLM-enhanced contextualized graphs. Subsequently, different modalities are jointly aligned through an asymmetric teacher-student graph neural network. (2) Online Multi-Perspective Evidence Reasoning leverages the power of LLM as a reasoning module to analyze the correlation and semantics of the multi-perspective evidence to induce an effective ranking strategy for accurate entity linking without supervision. Extensive experiments on widely used MEL benchmarks demonstrate that MSR-MEL consistently outperforms state-of-the-art unsupervised methods. The source code of this paper was available at: https://anonymous.4open.science/r/MSR-MEL-C21E/.
title Multi-Perspective Evidence Synthesis and Reasoning for Unsupervised Multimodal Entity Linking
topic Computation and Language
url https://arxiv.org/abs/2604.20283