@inproceedings{li-etal-2025-llms,
title = "How {LLM}s React to Industrial Spatio-Temporal Data? Assessing Hallucination with a Novel Traffic Incident Benchmark Dataset",
author = "Li, Qiang and
Tan, Mingkun and
Zhao, Xun and
Zhang, Dan and
Zhang, Daoan and
Lei, Shengzhao and
Chu, Anderson S. and
Li, Lujun and
Kamnoedboon, Porawit",
editor = "Chen, Weizhu and
Yang, Yi and
Kachuee, Mohammad and
Fu, Xue-Yong",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-industry.4/",
doi = "10.18653/v1/2025.naacl-industry.4",
pages = "36--53",
ISBN = "979-8-89176-194-0",
abstract = "Large language models (LLMs) hold revolutionary potential to digitize and enhance the Health {\&} Public Services (H{\&}PS) industry. Despite their advanced linguistic abilities, concerns about accuracy, stability, and traceability still persist, especially in high-stakes areas such as transportation systems. Moreover, the predominance of English in LLM development raises questions about how they perform in non-English contexts. This study originated from a real world industrial GenAI application, introduces a novel cross-lingual benchmark dataset comprising nearly 99,869 real traffic incident records from Vienna (2013-2023) to assess the robustness of state-of-the-art LLMs ($\geq$ 9) in the spatio vs temporal domain for traffic incident classification. We then explored three hypotheses {---} sentence indexing, date-to-text conversion, and German-to-English translation {---} and incorporated Retrieval Augmented Generation (RAG) to further examine the LLM hallucinations in both spatial and temporal domain. Our experiments reveal significant performance disparities in the spatio-temporal domain and demonstrate what types of hallucinations that RAG can mitigate and how it achieves this. We also provide open access to our H{\&}PS traffic incident dataset, with the project demo and code available at Website \url{https://sites.google.com/view/llmhallucination/home}"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2025-llms">
<titleInfo>
<title>How LLMs React to Industrial Spatio-Temporal Data? Assessing Hallucination with a Novel Traffic Incident Benchmark Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qiang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingkun</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xun</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daoan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shengzhao</namePart>
<namePart type="family">Lei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anderson</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Chu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lujun</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Porawit</namePart>
<namePart type="family">Kamnoedboon</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>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weizhu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Kachuee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xue-Yong</namePart>
<namePart type="family">Fu</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">979-8-89176-194-0</identifier>
</relatedItem>
<abstract>Large language models (LLMs) hold revolutionary potential to digitize and enhance the Health & Public Services (H&PS) industry. Despite their advanced linguistic abilities, concerns about accuracy, stability, and traceability still persist, especially in high-stakes areas such as transportation systems. Moreover, the predominance of English in LLM development raises questions about how they perform in non-English contexts. This study originated from a real world industrial GenAI application, introduces a novel cross-lingual benchmark dataset comprising nearly 99,869 real traffic incident records from Vienna (2013-2023) to assess the robustness of state-of-the-art LLMs (\geq 9) in the spatio vs temporal domain for traffic incident classification. We then explored three hypotheses — sentence indexing, date-to-text conversion, and German-to-English translation — and incorporated Retrieval Augmented Generation (RAG) to further examine the LLM hallucinations in both spatial and temporal domain. Our experiments reveal significant performance disparities in the spatio-temporal domain and demonstrate what types of hallucinations that RAG can mitigate and how it achieves this. We also provide open access to our H&PS traffic incident dataset, with the project demo and code available at Website https://sites.google.com/view/llmhallucination/home</abstract>
<identifier type="citekey">li-etal-2025-llms</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-industry.4</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-industry.4/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>36</start>
<end>53</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How LLMs React to Industrial Spatio-Temporal Data? Assessing Hallucination with a Novel Traffic Incident Benchmark Dataset
%A Li, Qiang
%A Tan, Mingkun
%A Zhao, Xun
%A Zhang, Dan
%A Zhang, Daoan
%A Lei, Shengzhao
%A Chu, Anderson S.
%A Li, Lujun
%A Kamnoedboon, Porawit
%Y Chen, Weizhu
%Y Yang, Yi
%Y Kachuee, Mohammad
%Y Fu, Xue-Yong
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-194-0
%F li-etal-2025-llms
%X Large language models (LLMs) hold revolutionary potential to digitize and enhance the Health & Public Services (H&PS) industry. Despite their advanced linguistic abilities, concerns about accuracy, stability, and traceability still persist, especially in high-stakes areas such as transportation systems. Moreover, the predominance of English in LLM development raises questions about how they perform in non-English contexts. This study originated from a real world industrial GenAI application, introduces a novel cross-lingual benchmark dataset comprising nearly 99,869 real traffic incident records from Vienna (2013-2023) to assess the robustness of state-of-the-art LLMs (\geq 9) in the spatio vs temporal domain for traffic incident classification. We then explored three hypotheses — sentence indexing, date-to-text conversion, and German-to-English translation — and incorporated Retrieval Augmented Generation (RAG) to further examine the LLM hallucinations in both spatial and temporal domain. Our experiments reveal significant performance disparities in the spatio-temporal domain and demonstrate what types of hallucinations that RAG can mitigate and how it achieves this. We also provide open access to our H&PS traffic incident dataset, with the project demo and code available at Website https://sites.google.com/view/llmhallucination/home
%R 10.18653/v1/2025.naacl-industry.4
%U https://aclanthology.org/2025.naacl-industry.4/
%U https://doi.org/10.18653/v1/2025.naacl-industry.4
%P 36-53
Markdown (Informal)
[How LLMs React to Industrial Spatio-Temporal Data? Assessing Hallucination with a Novel Traffic Incident Benchmark Dataset](https://aclanthology.org/2025.naacl-industry.4/) (Li et al., NAACL 2025)
ACL
- Qiang Li, Mingkun Tan, Xun Zhao, Dan Zhang, Daoan Zhang, Shengzhao Lei, Anderson S. Chu, Lujun Li, and Porawit Kamnoedboon. 2025. How LLMs React to Industrial Spatio-Temporal Data? Assessing Hallucination with a Novel Traffic Incident Benchmark Dataset. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track), pages 36–53, Albuquerque, New Mexico. Association for Computational Linguistics.