<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="estevanell-valladares-etal-2025-xautolm">
    <titleInfo>
        <title>XAutoLM: Efficient Fine-Tuning of Language Models via Meta-Learning and AutoML</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ernesto</namePart>
        <namePart type="given">Luis</namePart>
        <namePart type="family">Estevanell Valladares</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Suilan</namePart>
        <namePart type="family">Estevez-Velarde</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yoan</namePart>
        <namePart type="family">Gutierrez</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Andrés</namePart>
        <namePart type="family">Montoyo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ruslan</namePart>
        <namePart type="family">Mitkov</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>Experts in machine learning leverage domain knowledge to navigate decisions in model selection, hyperparameter optimization, and resource allocation. This is particularly critical for fine-tuning language models (LMs), where repeated trials incur substantial computational overhead and environmental impact. However, no existing automated framework simultaneously tackles the entire model selection and hyperparameter optimization (HPO) task for resource-efficient LM fine-tuning. We introduce XAutoLM, a meta-learning-augmented AutoML framework that reuses past experiences to optimize discriminative and generative LM fine-tuning pipelines efficiently. XAutoLM learns from stored successes and failures by extracting task- and system-level meta-features to bias its sampling toward valuable configurations and away from costly dead ends. On four text classification and two question-answering benchmarks, XAutoLM surpasses zero-shot optimizer’s peak F1 on five of six tasks, cuts mean evaluation time of pipelines by up to 4.5x, reduces search error ratios by up to sevenfold, and uncovers up to 50% more pipelines above the zero-shot Pareto front. In contrast, simpler memory-based baselines suffer negative transfer. We release XAutoLM and our experience store to catalyze resource-efficient, Green AI fine-tuning in the NLP community.</abstract>
    <identifier type="citekey">estevanell-valladares-etal-2025-xautolm</identifier>
    <location>
        <url>https://aclanthology.org/2025.emnlp-main.399/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>7874</start>
            <end>7891</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T XAutoLM: Efficient Fine-Tuning of Language Models via Meta-Learning and AutoML
%A Estevanell Valladares, Ernesto Luis
%A Estevez-Velarde, Suilan
%A Gutierrez, Yoan
%A Montoyo, Andrés
%A Mitkov, Ruslan
%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 estevanell-valladares-etal-2025-xautolm
%X Experts in machine learning leverage domain knowledge to navigate decisions in model selection, hyperparameter optimization, and resource allocation. This is particularly critical for fine-tuning language models (LMs), where repeated trials incur substantial computational overhead and environmental impact. However, no existing automated framework simultaneously tackles the entire model selection and hyperparameter optimization (HPO) task for resource-efficient LM fine-tuning. We introduce XAutoLM, a meta-learning-augmented AutoML framework that reuses past experiences to optimize discriminative and generative LM fine-tuning pipelines efficiently. XAutoLM learns from stored successes and failures by extracting task- and system-level meta-features to bias its sampling toward valuable configurations and away from costly dead ends. On four text classification and two question-answering benchmarks, XAutoLM surpasses zero-shot optimizer’s peak F1 on five of six tasks, cuts mean evaluation time of pipelines by up to 4.5x, reduces search error ratios by up to sevenfold, and uncovers up to 50% more pipelines above the zero-shot Pareto front. In contrast, simpler memory-based baselines suffer negative transfer. We release XAutoLM and our experience store to catalyze resource-efficient, Green AI fine-tuning in the NLP community.
%U https://aclanthology.org/2025.emnlp-main.399/
%P 7874-7891

Markdown (Informal)

[XAutoLM: Efficient Fine-Tuning of Language Models via Meta-Learning and AutoML](https://aclanthology.org/2025.emnlp-main.399/) (Estevanell Valladares et al., EMNLP 2025)

• XAutoLM: Efficient Fine-Tuning of Language Models via Meta-Learning and AutoML (Estevanell Valladares et al., EMNLP 2025)

ACL

• Ernesto Luis Estevanell Valladares, Suilan Estevez-Velarde, Yoan Gutierrez, Andrés Montoyo, and Ruslan Mitkov. 2025. XAutoLM: Efficient Fine-Tuning of Language Models via Meta-Learning and AutoML. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 7874–7891, Suzhou, China. Association for Computational Linguistics.