@inproceedings{yin-etal-2025-talk,
title = "How to Talk to Language Models: Serialization Strategies for Structured Entity Matching",
author = "Yin, Haoteng and
Kim, Jinha and
Mathur, Prashant and
Sarker, Krishanu and
Bansal, Vidit",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.437/",
doi = "10.18653/v1/2025.findings-naacl.437",
pages = "7836--7850",
ISBN = "979-8-89176-195-7",
abstract = "Entity matching (EM), which identifies whether two data records refer to the same real-world entity, is crucial for knowledge base construction and enhancing data-driven AI systems. Recent advances in language models (LMs) have shown great potential in resolving entities with rich textual attributes. However, their performance heavily depends on how structured entities are ``talked'' through serialized text. The impact of this serialization process remains underexplored, particularly for entities with complex relations in knowledge graphs (KGs). In this work, we systematically study entity serialization by benchmarking the effect of common schemes with LMs of different sizes on diverse tabular matching datasets. We apply our findings to propose a novel serialization scheme for KG entities based on random walks and utilize LLMs to encode sampled semantic walks for matching. Using this lightweight approach with open-source LLMs, we achieve a leading performance on EM in canonical and highly heterogeneous KGs, demonstrating significant throughput increases and superior robustness compared to GPT-4-based methods. Our study on serialization provides valuable insights for the deployment of LMs in real-world EM tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yin-etal-2025-talk">
<titleInfo>
<title>How to Talk to Language Models: Serialization Strategies for Structured Entity Matching</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haoteng</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinha</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prashant</namePart>
<namePart type="family">Mathur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Krishanu</namePart>
<namePart type="family">Sarker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vidit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-195-7</identifier>
</relatedItem>
<abstract>Entity matching (EM), which identifies whether two data records refer to the same real-world entity, is crucial for knowledge base construction and enhancing data-driven AI systems. Recent advances in language models (LMs) have shown great potential in resolving entities with rich textual attributes. However, their performance heavily depends on how structured entities are “talked” through serialized text. The impact of this serialization process remains underexplored, particularly for entities with complex relations in knowledge graphs (KGs). In this work, we systematically study entity serialization by benchmarking the effect of common schemes with LMs of different sizes on diverse tabular matching datasets. We apply our findings to propose a novel serialization scheme for KG entities based on random walks and utilize LLMs to encode sampled semantic walks for matching. Using this lightweight approach with open-source LLMs, we achieve a leading performance on EM in canonical and highly heterogeneous KGs, demonstrating significant throughput increases and superior robustness compared to GPT-4-based methods. Our study on serialization provides valuable insights for the deployment of LMs in real-world EM tasks.</abstract>
<identifier type="citekey">yin-etal-2025-talk</identifier>
<identifier type="doi">10.18653/v1/2025.findings-naacl.437</identifier>
<location>
<url>https://aclanthology.org/2025.findings-naacl.437/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>7836</start>
<end>7850</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How to Talk to Language Models: Serialization Strategies for Structured Entity Matching
%A Yin, Haoteng
%A Kim, Jinha
%A Mathur, Prashant
%A Sarker, Krishanu
%A Bansal, Vidit
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F yin-etal-2025-talk
%X Entity matching (EM), which identifies whether two data records refer to the same real-world entity, is crucial for knowledge base construction and enhancing data-driven AI systems. Recent advances in language models (LMs) have shown great potential in resolving entities with rich textual attributes. However, their performance heavily depends on how structured entities are “talked” through serialized text. The impact of this serialization process remains underexplored, particularly for entities with complex relations in knowledge graphs (KGs). In this work, we systematically study entity serialization by benchmarking the effect of common schemes with LMs of different sizes on diverse tabular matching datasets. We apply our findings to propose a novel serialization scheme for KG entities based on random walks and utilize LLMs to encode sampled semantic walks for matching. Using this lightweight approach with open-source LLMs, we achieve a leading performance on EM in canonical and highly heterogeneous KGs, demonstrating significant throughput increases and superior robustness compared to GPT-4-based methods. Our study on serialization provides valuable insights for the deployment of LMs in real-world EM tasks.
%R 10.18653/v1/2025.findings-naacl.437
%U https://aclanthology.org/2025.findings-naacl.437/
%U https://doi.org/10.18653/v1/2025.findings-naacl.437
%P 7836-7850
Markdown (Informal)
[How to Talk to Language Models: Serialization Strategies for Structured Entity Matching](https://aclanthology.org/2025.findings-naacl.437/) (Yin et al., Findings 2025)
ACL