@inproceedings{lin-etal-2025-makar,
title = "{MAKAR}: a Multi-Agent framework based Knowledge-Augmented Reasoning for Grounded Multimodal Named Entity Recognition",
author = "Lin, Xinkui and
Zhang, Yuhui and
Xu, Yongxiu and
Huang, Kun and
Mu, Hongzhang and
Wang, Yubin and
Gou, Gaopeng and
Qian, Li and
Peng, Li and
Liu, Wei and
Luan, Jian and
Xu, Hongbo",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.311/",
pages = "6121--6141",
ISBN = "979-8-89176-332-6",
abstract = "Grounded Multimodal Named Entity Recognition (GMNER), which aims to extract textual entities, their types, and corresponding visual regions from image-text data, has become a critical task in multimodal information extraction. However, existing methods face two major challenges. First, they fail to address the semantic ambiguity caused by polysemy and the long-tail distribution of datasets. Second, unlike visual grounding which provides descriptive phrases, entity grounding only offers brief entity names which carry less semantic information. Current methods lack sufficient semantic interaction between text and image, hindering accurate entity-visual region matching. To tackle these issues, we propose MAKAR, a Multi-Agent framework based Knowledge-Augmented Reasoning, comprising three agents: Knowledge Enhancement, Entity Correction, and Entity Reasoning Grounding. Specifically, in the named entity recognition phase, the Knowledge Enhancement Agent leverages a Multimodal Large Language Model (MLLM) as an implicit knowledge base to enhance ambiguous image-text content with its internal knowledge. For samples with low-confidence entity boundaries and types, the Entity Correction Agent uses web search tools to retrieve and summarize relevant web content, thereby correcting entities using both internal and external knowledge. In the entity grounding phase, the Entity Reasoning Grounding Agent utilizes multi-step Chain-of-Thought reasoning to perform grounding for each entity. Extensive experiments show that MAKAR achieves state-of-the-art performance on two benchmark datasets. Code is available at: https://github.com/Nikol-coder/MAKAR."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-etal-2025-makar">
<titleInfo>
<title>MAKAR: a Multi-Agent framework based Knowledge-Augmented Reasoning for Grounded Multimodal Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinkui</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuhui</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongxiu</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kun</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongzhang</namePart>
<namePart type="family">Mu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yubin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaopeng</namePart>
<namePart type="family">Gou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Qian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Luan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongbo</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Grounded Multimodal Named Entity Recognition (GMNER), which aims to extract textual entities, their types, and corresponding visual regions from image-text data, has become a critical task in multimodal information extraction. However, existing methods face two major challenges. First, they fail to address the semantic ambiguity caused by polysemy and the long-tail distribution of datasets. Second, unlike visual grounding which provides descriptive phrases, entity grounding only offers brief entity names which carry less semantic information. Current methods lack sufficient semantic interaction between text and image, hindering accurate entity-visual region matching. To tackle these issues, we propose MAKAR, a Multi-Agent framework based Knowledge-Augmented Reasoning, comprising three agents: Knowledge Enhancement, Entity Correction, and Entity Reasoning Grounding. Specifically, in the named entity recognition phase, the Knowledge Enhancement Agent leverages a Multimodal Large Language Model (MLLM) as an implicit knowledge base to enhance ambiguous image-text content with its internal knowledge. For samples with low-confidence entity boundaries and types, the Entity Correction Agent uses web search tools to retrieve and summarize relevant web content, thereby correcting entities using both internal and external knowledge. In the entity grounding phase, the Entity Reasoning Grounding Agent utilizes multi-step Chain-of-Thought reasoning to perform grounding for each entity. Extensive experiments show that MAKAR achieves state-of-the-art performance on two benchmark datasets. Code is available at: https://github.com/Nikol-coder/MAKAR.</abstract>
<identifier type="citekey">lin-etal-2025-makar</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.311/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>6121</start>
<end>6141</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MAKAR: a Multi-Agent framework based Knowledge-Augmented Reasoning for Grounded Multimodal Named Entity Recognition
%A Lin, Xinkui
%A Zhang, Yuhui
%A Xu, Yongxiu
%A Huang, Kun
%A Mu, Hongzhang
%A Wang, Yubin
%A Gou, Gaopeng
%A Qian, Li
%A Peng, Li
%A Liu, Wei
%A Luan, Jian
%A Xu, Hongbo
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F lin-etal-2025-makar
%X Grounded Multimodal Named Entity Recognition (GMNER), which aims to extract textual entities, their types, and corresponding visual regions from image-text data, has become a critical task in multimodal information extraction. However, existing methods face two major challenges. First, they fail to address the semantic ambiguity caused by polysemy and the long-tail distribution of datasets. Second, unlike visual grounding which provides descriptive phrases, entity grounding only offers brief entity names which carry less semantic information. Current methods lack sufficient semantic interaction between text and image, hindering accurate entity-visual region matching. To tackle these issues, we propose MAKAR, a Multi-Agent framework based Knowledge-Augmented Reasoning, comprising three agents: Knowledge Enhancement, Entity Correction, and Entity Reasoning Grounding. Specifically, in the named entity recognition phase, the Knowledge Enhancement Agent leverages a Multimodal Large Language Model (MLLM) as an implicit knowledge base to enhance ambiguous image-text content with its internal knowledge. For samples with low-confidence entity boundaries and types, the Entity Correction Agent uses web search tools to retrieve and summarize relevant web content, thereby correcting entities using both internal and external knowledge. In the entity grounding phase, the Entity Reasoning Grounding Agent utilizes multi-step Chain-of-Thought reasoning to perform grounding for each entity. Extensive experiments show that MAKAR achieves state-of-the-art performance on two benchmark datasets. Code is available at: https://github.com/Nikol-coder/MAKAR.
%U https://aclanthology.org/2025.emnlp-main.311/
%P 6121-6141
Markdown (Informal)
[MAKAR: a Multi-Agent framework based Knowledge-Augmented Reasoning for Grounded Multimodal Named Entity Recognition](https://aclanthology.org/2025.emnlp-main.311/) (Lin et al., EMNLP 2025)
ACL
- Xinkui Lin, Yuhui Zhang, Yongxiu Xu, Kun Huang, Hongzhang Mu, Yubin Wang, Gaopeng Gou, Li Qian, Li Peng, Wei Liu, Jian Luan, and Hongbo Xu. 2025. MAKAR: a Multi-Agent framework based Knowledge-Augmented Reasoning for Grounded Multimodal Named Entity Recognition. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 6121–6141, Suzhou, China. Association for Computational Linguistics.