@inproceedings{zhang-etal-2025-evaluating,
title = "Evaluating Large Language Models with Enterprise Benchmarks",
author = "Zhang, Bing and
Takeuchi, Mikio and
Kawahara, Ryo and
Asthana, Shubhi and
Hossain, Md. Maruf and
Ren, Guang-Jie and
Soule, Kate and
Mai, Yifan and
Zhu, Yada",
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.40/",
doi = "10.18653/v1/2025.naacl-industry.40",
pages = "485--505",
ISBN = "979-8-89176-194-0",
abstract = "The advancement of large language models (LLMs) has led to a greater challenge of having a rigorous and systematic evaluation of complex tasks performed, especially in enterprise applications. Therefore, LLMs need to be benchmarked with enterprise datasets for a variety of NLP tasks. This work explores benchmarking strategies focused on LLM evaluation, with a specific emphasis on both English and Japanese. The proposed evaluation framework encompasses 25 publicly available domain-specific English benchmarks from diverse enterprise domains like financial services, legal, climate, cyber security, and 2 public Japanese finance benchmarks. The diverse performance of 8 models across different enterprise tasks highlights the importance of selecting the right model based on the specific requirements of each task. Code and prompts are available on GitHub."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2025-evaluating">
<titleInfo>
<title>Evaluating Large Language Models with Enterprise Benchmarks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikio</namePart>
<namePart type="family">Takeuchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryo</namePart>
<namePart type="family">Kawahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shubhi</namePart>
<namePart type="family">Asthana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Maruf</namePart>
<namePart type="family">Hossain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guang-Jie</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kate</namePart>
<namePart type="family">Soule</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifan</namePart>
<namePart type="family">Mai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yada</namePart>
<namePart type="family">Zhu</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>The advancement of large language models (LLMs) has led to a greater challenge of having a rigorous and systematic evaluation of complex tasks performed, especially in enterprise applications. Therefore, LLMs need to be benchmarked with enterprise datasets for a variety of NLP tasks. This work explores benchmarking strategies focused on LLM evaluation, with a specific emphasis on both English and Japanese. The proposed evaluation framework encompasses 25 publicly available domain-specific English benchmarks from diverse enterprise domains like financial services, legal, climate, cyber security, and 2 public Japanese finance benchmarks. The diverse performance of 8 models across different enterprise tasks highlights the importance of selecting the right model based on the specific requirements of each task. Code and prompts are available on GitHub.</abstract>
<identifier type="citekey">zhang-etal-2025-evaluating</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-industry.40</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-industry.40/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>485</start>
<end>505</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Large Language Models with Enterprise Benchmarks
%A Zhang, Bing
%A Takeuchi, Mikio
%A Kawahara, Ryo
%A Asthana, Shubhi
%A Hossain, Md. Maruf
%A Ren, Guang-Jie
%A Soule, Kate
%A Mai, Yifan
%A Zhu, Yada
%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 zhang-etal-2025-evaluating
%X The advancement of large language models (LLMs) has led to a greater challenge of having a rigorous and systematic evaluation of complex tasks performed, especially in enterprise applications. Therefore, LLMs need to be benchmarked with enterprise datasets for a variety of NLP tasks. This work explores benchmarking strategies focused on LLM evaluation, with a specific emphasis on both English and Japanese. The proposed evaluation framework encompasses 25 publicly available domain-specific English benchmarks from diverse enterprise domains like financial services, legal, climate, cyber security, and 2 public Japanese finance benchmarks. The diverse performance of 8 models across different enterprise tasks highlights the importance of selecting the right model based on the specific requirements of each task. Code and prompts are available on GitHub.
%R 10.18653/v1/2025.naacl-industry.40
%U https://aclanthology.org/2025.naacl-industry.40/
%U https://doi.org/10.18653/v1/2025.naacl-industry.40
%P 485-505
Markdown (Informal)
[Evaluating Large Language Models with Enterprise Benchmarks](https://aclanthology.org/2025.naacl-industry.40/) (Zhang et al., NAACL 2025)
ACL
- Bing Zhang, Mikio Takeuchi, Ryo Kawahara, Shubhi Asthana, Md. Maruf Hossain, Guang-Jie Ren, Kate Soule, Yifan Mai, and Yada Zhu. 2025. Evaluating Large Language Models with Enterprise Benchmarks. 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 485–505, Albuquerque, New Mexico. Association for Computational Linguistics.