@inproceedings{van-thin-etal-2025-automotive,
title = "Automotive Document Labeling Using Large Language Models",
author = "Van Thin, Dang and
Chu, Cuong Xuan and
Graf, Christian and
Kaminski, Tobias and
Tran, Trung-Kien",
editor = "Potdar, Saloni and
Rojas-Barahona, Lina and
Montella, Sebastien",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = nov,
year = "2025",
address = "Suzhou (China)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-industry.112/",
pages = "1588--1595",
ISBN = "979-8-89176-333-3",
abstract = "Repairing and maintaining car parts are crucial tasks in the automotive industry, requiring a mechanic to have all relevant technical documents available. However, retrieving the right documents from a huge database heavily depends on domain expertise and is time consuming and error-prone. By labeling available documents according to the components they relate to, concise and accurate information can be retrieved efficiently. However, this is a challenging task as the relevance of a document to a particular component strongly depends on the context and the expertise of the domain specialist. Moreover, component terminology varies widely between different manufacturers. We address these challenges by utilizing Large Language Models (LLMs) to enrich and unify a component database via web mining, extracting relevant keywords, and leveraging hybrid search and LLM-based re-ranking to select the most relevant component for a document. We systematically evaluate our method using various LLMs on an expert-annotated dataset and demonstrate that it outperforms the baselines, which rely solely on LLM prompting."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="van-thin-etal-2025-automotive">
<titleInfo>
<title>Automotive Document Labeling Using Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dang</namePart>
<namePart type="family">Van Thin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cuong</namePart>
<namePart type="given">Xuan</namePart>
<namePart type="family">Chu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Graf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tobias</namePart>
<namePart type="family">Kaminski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trung-Kien</namePart>
<namePart type="family">Tran</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: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saloni</namePart>
<namePart type="family">Potdar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lina</namePart>
<namePart type="family">Rojas-Barahona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastien</namePart>
<namePart type="family">Montella</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">979-8-89176-333-3</identifier>
</relatedItem>
<abstract>Repairing and maintaining car parts are crucial tasks in the automotive industry, requiring a mechanic to have all relevant technical documents available. However, retrieving the right documents from a huge database heavily depends on domain expertise and is time consuming and error-prone. By labeling available documents according to the components they relate to, concise and accurate information can be retrieved efficiently. However, this is a challenging task as the relevance of a document to a particular component strongly depends on the context and the expertise of the domain specialist. Moreover, component terminology varies widely between different manufacturers. We address these challenges by utilizing Large Language Models (LLMs) to enrich and unify a component database via web mining, extracting relevant keywords, and leveraging hybrid search and LLM-based re-ranking to select the most relevant component for a document. We systematically evaluate our method using various LLMs on an expert-annotated dataset and demonstrate that it outperforms the baselines, which rely solely on LLM prompting.</abstract>
<identifier type="citekey">van-thin-etal-2025-automotive</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-industry.112/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>1588</start>
<end>1595</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automotive Document Labeling Using Large Language Models
%A Van Thin, Dang
%A Chu, Cuong Xuan
%A Graf, Christian
%A Kaminski, Tobias
%A Tran, Trung-Kien
%Y Potdar, Saloni
%Y Rojas-Barahona, Lina
%Y Montella, Sebastien
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou (China)
%@ 979-8-89176-333-3
%F van-thin-etal-2025-automotive
%X Repairing and maintaining car parts are crucial tasks in the automotive industry, requiring a mechanic to have all relevant technical documents available. However, retrieving the right documents from a huge database heavily depends on domain expertise and is time consuming and error-prone. By labeling available documents according to the components they relate to, concise and accurate information can be retrieved efficiently. However, this is a challenging task as the relevance of a document to a particular component strongly depends on the context and the expertise of the domain specialist. Moreover, component terminology varies widely between different manufacturers. We address these challenges by utilizing Large Language Models (LLMs) to enrich and unify a component database via web mining, extracting relevant keywords, and leveraging hybrid search and LLM-based re-ranking to select the most relevant component for a document. We systematically evaluate our method using various LLMs on an expert-annotated dataset and demonstrate that it outperforms the baselines, which rely solely on LLM prompting.
%U https://aclanthology.org/2025.emnlp-industry.112/
%P 1588-1595
Markdown (Informal)
[Automotive Document Labeling Using Large Language Models](https://aclanthology.org/2025.emnlp-industry.112/) (Van Thin et al., EMNLP 2025)
ACL
- Dang Van Thin, Cuong Xuan Chu, Christian Graf, Tobias Kaminski, and Trung-Kien Tran. 2025. Automotive Document Labeling Using Large Language Models. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 1588–1595, Suzhou (China). Association for Computational Linguistics.