@inproceedings{lin-etal-2025-efficient,
title = "Efficient Model Development through Fine-tuning Transfer",
author = "Lin, Pin-Jie and
Balasubramanian, Rishab and
Liu, Fengyuan and
Kandpal, Nikhil and
Vu, Tu",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.131/",
doi = "10.18653/v1/2025.emnlp-main.131",
pages = "2617--2636",
ISBN = "979-8-89176-332-6",
abstract = "Modern LLMs face a major obstacle: each new pre-trained model version requires expensive and repetitive alignment. We propose a method that transfers fine-tuning updates across model versions. The key idea is to extract the *diff vector*, which is the difference in parameters induced by fine-tuning, from a *source* model version and apply it to the base of a different *target* version. We show that transferring diff vectors significantly improves the target base model, often achieving performance comparable to its fine-tuned counterpart. For example, applying the fine-tuning updates from Llama 3.0 8B to Llama 3.1 8B increases accuracy by 46.9{\%} on IFEval and 15.7{\%} on LiveCodeBench without further training, surpassing Llama 3.1 8B Instruct. In multilingual settings, we also observe accuracy gains relative to Llama 3.1 8B Instruct, including 4.7{\%} for Malagasy and 15.5{\%} for Turkish on Global MMLU. Our controlled experiments reveal that fine-tuning transfer works best when source and target models are linearly connected in parameter space. We also show that this transfer provides a stronger and more efficient starting point for subsequent fine-tuning. Finally, we propose an iterative *recycling-then-finetuning* approach for continuous model development, which improves both efficiency and effectiveness. Our findings suggest that fine-tuning transfer is a viable strategy to reduce training costs while maintaining model performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-etal-2025-efficient">
<titleInfo>
<title>Efficient Model Development through Fine-tuning Transfer</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pin-Jie</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rishab</namePart>
<namePart type="family">Balasubramanian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fengyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikhil</namePart>
<namePart type="family">Kandpal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tu</namePart>
<namePart type="family">Vu</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</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">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Modern LLMs face a major obstacle: each new pre-trained model version requires expensive and repetitive alignment. We propose a method that transfers fine-tuning updates across model versions. The key idea is to extract the *diff vector*, which is the difference in parameters induced by fine-tuning, from a *source* model version and apply it to the base of a different *target* version. We show that transferring diff vectors significantly improves the target base model, often achieving performance comparable to its fine-tuned counterpart. For example, applying the fine-tuning updates from Llama 3.0 8B to Llama 3.1 8B increases accuracy by 46.9% on IFEval and 15.7% on LiveCodeBench without further training, surpassing Llama 3.1 8B Instruct. In multilingual settings, we also observe accuracy gains relative to Llama 3.1 8B Instruct, including 4.7% for Malagasy and 15.5% for Turkish on Global MMLU. Our controlled experiments reveal that fine-tuning transfer works best when source and target models are linearly connected in parameter space. We also show that this transfer provides a stronger and more efficient starting point for subsequent fine-tuning. Finally, we propose an iterative *recycling-then-finetuning* approach for continuous model development, which improves both efficiency and effectiveness. Our findings suggest that fine-tuning transfer is a viable strategy to reduce training costs while maintaining model performance.</abstract>
<identifier type="citekey">lin-etal-2025-efficient</identifier>
<identifier type="doi">10.18653/v1/2025.emnlp-main.131</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.131/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>2617</start>
<end>2636</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Efficient Model Development through Fine-tuning Transfer
%A Lin, Pin-Jie
%A Balasubramanian, Rishab
%A Liu, Fengyuan
%A Kandpal, Nikhil
%A Vu, Tu
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F lin-etal-2025-efficient
%X Modern LLMs face a major obstacle: each new pre-trained model version requires expensive and repetitive alignment. We propose a method that transfers fine-tuning updates across model versions. The key idea is to extract the *diff vector*, which is the difference in parameters induced by fine-tuning, from a *source* model version and apply it to the base of a different *target* version. We show that transferring diff vectors significantly improves the target base model, often achieving performance comparable to its fine-tuned counterpart. For example, applying the fine-tuning updates from Llama 3.0 8B to Llama 3.1 8B increases accuracy by 46.9% on IFEval and 15.7% on LiveCodeBench without further training, surpassing Llama 3.1 8B Instruct. In multilingual settings, we also observe accuracy gains relative to Llama 3.1 8B Instruct, including 4.7% for Malagasy and 15.5% for Turkish on Global MMLU. Our controlled experiments reveal that fine-tuning transfer works best when source and target models are linearly connected in parameter space. We also show that this transfer provides a stronger and more efficient starting point for subsequent fine-tuning. Finally, we propose an iterative *recycling-then-finetuning* approach for continuous model development, which improves both efficiency and effectiveness. Our findings suggest that fine-tuning transfer is a viable strategy to reduce training costs while maintaining model performance.
%R 10.18653/v1/2025.emnlp-main.131
%U https://aclanthology.org/2025.emnlp-main.131/
%U https://doi.org/10.18653/v1/2025.emnlp-main.131
%P 2617-2636
Markdown (Informal)
[Efficient Model Development through Fine-tuning Transfer](https://aclanthology.org/2025.emnlp-main.131/) (Lin et al., EMNLP 2025)
ACL
- Pin-Jie Lin, Rishab Balasubramanian, Fengyuan Liu, Nikhil Kandpal, and Tu Vu. 2025. Efficient Model Development through Fine-tuning Transfer. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 2617–2636, Suzhou, China. Association for Computational Linguistics.