@inproceedings{huang-etal-2025-damoc,
title = "{D}a{M}o{C}: Efficiently Selecting the Optimal Large Language Model for Fine-tuning Domain Tasks Based on Data and Model Compression",
author = "Huang, Wei and
Wei, Huang and
Wang, Yinggui",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.699/",
doi = "10.18653/v1/2025.findings-emnlp.699",
pages = "13012--13027",
ISBN = "979-8-89176-335-7",
abstract = "Large language models (LLMs) excel in general tasks but struggle with domain-specific ones, requiring fine-tuning with specific data. With many open-source LLMs available, selecting the best model for fine-tuning downstream tasks is challenging, primarily focusing on how to quickly identify the optimal LLM. We introduce a Data and Model Compression Framework (DaMoC) that addresses this challenge by: 1) Data Level: A systematic categorization of data filtering methodologies for LLMs is first established, classifying them into three distinct paradigms: (1) distribution-aware methods, (2) quality-aware methods, and (3) hybrid approaches considering both dimensions. Further, we enhance the density of key tokens in the text achieving token compression. Subsequently, we use an LLM to iterative rewrite the text to optimize its expression. 2) Model Level: We use layer similarity scores to assess each layer{'}s importance and remove those with lower importance. Then, we introduce a sparse merging paradigm to preserve as much of the original model{'}s capability as possible. Extensive experiments on four datasets, medical Q{\&}A, financial Q{\&}A, general Q{\&}A, and reading comprehension, show that we can select the optimal LLM while saving approximately 20-fold in training time."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2025-damoc">
<titleInfo>
<title>DaMoC: Efficiently Selecting the Optimal Large Language Model for Fine-tuning Domain Tasks Based on Data and Model Compression</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huang</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yinggui</namePart>
<namePart type="family">Wang</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>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</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">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Large language models (LLMs) excel in general tasks but struggle with domain-specific ones, requiring fine-tuning with specific data. With many open-source LLMs available, selecting the best model for fine-tuning downstream tasks is challenging, primarily focusing on how to quickly identify the optimal LLM. We introduce a Data and Model Compression Framework (DaMoC) that addresses this challenge by: 1) Data Level: A systematic categorization of data filtering methodologies for LLMs is first established, classifying them into three distinct paradigms: (1) distribution-aware methods, (2) quality-aware methods, and (3) hybrid approaches considering both dimensions. Further, we enhance the density of key tokens in the text achieving token compression. Subsequently, we use an LLM to iterative rewrite the text to optimize its expression. 2) Model Level: We use layer similarity scores to assess each layer’s importance and remove those with lower importance. Then, we introduce a sparse merging paradigm to preserve as much of the original model’s capability as possible. Extensive experiments on four datasets, medical Q&A, financial Q&A, general Q&A, and reading comprehension, show that we can select the optimal LLM while saving approximately 20-fold in training time.</abstract>
<identifier type="citekey">huang-etal-2025-damoc</identifier>
<identifier type="doi">10.18653/v1/2025.findings-emnlp.699</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.699/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>13012</start>
<end>13027</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DaMoC: Efficiently Selecting the Optimal Large Language Model for Fine-tuning Domain Tasks Based on Data and Model Compression
%A Huang, Wei
%A Wei, Huang
%A Wang, Yinggui
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F huang-etal-2025-damoc
%X Large language models (LLMs) excel in general tasks but struggle with domain-specific ones, requiring fine-tuning with specific data. With many open-source LLMs available, selecting the best model for fine-tuning downstream tasks is challenging, primarily focusing on how to quickly identify the optimal LLM. We introduce a Data and Model Compression Framework (DaMoC) that addresses this challenge by: 1) Data Level: A systematic categorization of data filtering methodologies for LLMs is first established, classifying them into three distinct paradigms: (1) distribution-aware methods, (2) quality-aware methods, and (3) hybrid approaches considering both dimensions. Further, we enhance the density of key tokens in the text achieving token compression. Subsequently, we use an LLM to iterative rewrite the text to optimize its expression. 2) Model Level: We use layer similarity scores to assess each layer’s importance and remove those with lower importance. Then, we introduce a sparse merging paradigm to preserve as much of the original model’s capability as possible. Extensive experiments on four datasets, medical Q&A, financial Q&A, general Q&A, and reading comprehension, show that we can select the optimal LLM while saving approximately 20-fold in training time.
%R 10.18653/v1/2025.findings-emnlp.699
%U https://aclanthology.org/2025.findings-emnlp.699/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.699
%P 13012-13027
Markdown (Informal)
[DaMoC: Efficiently Selecting the Optimal Large Language Model for Fine-tuning Domain Tasks Based on Data and Model Compression](https://aclanthology.org/2025.findings-emnlp.699/) (Huang et al., Findings 2025)
ACL