@inproceedings{guo-etal-2025-sdbench,
title = "{SDB}ench: A Survey-based Domain-specific {LLM} Benchmarking and Optimization Framework",
author = "Guo, Cheng and
Kai, Hu and
Liang, Shuxian and
Jiang, Yiyang and
Gao, Yi and
Hua, Xian-Sheng and
Dong, Wei",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.662/",
doi = "10.18653/v1/2025.acl-long.662",
pages = "13492--13506",
ISBN = "979-8-89176-251-0",
abstract = "The rapid advancement of large language models (LLMs) in recent years has made it feasible to establish domain-specific LLMs for specialized fields. However, in practical development, acquiring domain-specific knowledge often requires a significant amount of professional expert manpower. Moreover, even when domain-specific data is available, the lack of a unified methodology for benchmark dataset establishment often results in uneven data distribution. This imbalance can lead to an inaccurate assessment of the true model capabilities during the evaluation of domain-specific LLMs. To address these challenges, we introduce **SDBench**, a generic framework for generating evaluation datasets for domain-specific LLMs. This method is also applicable for establishing the LLM instruction datasets. It significantly reduces the reliance on expert manpower while ensuring that the collected data is uniformly distributed. To validate the effectiveness of this framework, we also present the **BridgeBench**, a novel benchmark for bridge engineering knowledge, and the **BridgeGPT**, the first LLM specialized in bridge engineering, which can solve bridge engineering tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2025-sdbench">
<titleInfo>
<title>SDBench: A Survey-based Domain-specific LLM Benchmarking and Optimization Framework</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cheng</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hu</namePart>
<namePart type="family">Kai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuxian</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiyang</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xian-Sheng</namePart>
<namePart type="family">Hua</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>The rapid advancement of large language models (LLMs) in recent years has made it feasible to establish domain-specific LLMs for specialized fields. However, in practical development, acquiring domain-specific knowledge often requires a significant amount of professional expert manpower. Moreover, even when domain-specific data is available, the lack of a unified methodology for benchmark dataset establishment often results in uneven data distribution. This imbalance can lead to an inaccurate assessment of the true model capabilities during the evaluation of domain-specific LLMs. To address these challenges, we introduce **SDBench**, a generic framework for generating evaluation datasets for domain-specific LLMs. This method is also applicable for establishing the LLM instruction datasets. It significantly reduces the reliance on expert manpower while ensuring that the collected data is uniformly distributed. To validate the effectiveness of this framework, we also present the **BridgeBench**, a novel benchmark for bridge engineering knowledge, and the **BridgeGPT**, the first LLM specialized in bridge engineering, which can solve bridge engineering tasks.</abstract>
<identifier type="citekey">guo-etal-2025-sdbench</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.662</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.662/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>13492</start>
<end>13506</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SDBench: A Survey-based Domain-specific LLM Benchmarking and Optimization Framework
%A Guo, Cheng
%A Kai, Hu
%A Liang, Shuxian
%A Jiang, Yiyang
%A Gao, Yi
%A Hua, Xian-Sheng
%A Dong, Wei
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F guo-etal-2025-sdbench
%X The rapid advancement of large language models (LLMs) in recent years has made it feasible to establish domain-specific LLMs for specialized fields. However, in practical development, acquiring domain-specific knowledge often requires a significant amount of professional expert manpower. Moreover, even when domain-specific data is available, the lack of a unified methodology for benchmark dataset establishment often results in uneven data distribution. This imbalance can lead to an inaccurate assessment of the true model capabilities during the evaluation of domain-specific LLMs. To address these challenges, we introduce **SDBench**, a generic framework for generating evaluation datasets for domain-specific LLMs. This method is also applicable for establishing the LLM instruction datasets. It significantly reduces the reliance on expert manpower while ensuring that the collected data is uniformly distributed. To validate the effectiveness of this framework, we also present the **BridgeBench**, a novel benchmark for bridge engineering knowledge, and the **BridgeGPT**, the first LLM specialized in bridge engineering, which can solve bridge engineering tasks.
%R 10.18653/v1/2025.acl-long.662
%U https://aclanthology.org/2025.acl-long.662/
%U https://doi.org/10.18653/v1/2025.acl-long.662
%P 13492-13506
Markdown (Informal)
[SDBench: A Survey-based Domain-specific LLM Benchmarking and Optimization Framework](https://aclanthology.org/2025.acl-long.662/) (Guo et al., ACL 2025)
ACL