@inproceedings{zhan-zhang-2025-towards,
title = "Towards Better Multi-task Learning: A Framework for Optimizing Dataset Combinations in Large Language Models",
author = "Zhan, Zaifu and
Zhang, Rui",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.297/",
doi = "10.18653/v1/2025.findings-naacl.297",
pages = "5373--5386",
ISBN = "979-8-89176-195-7",
abstract = "To efficiently select optimal dataset combinations for enhancing multi-task learning (MTL) performance in large language models, we proposed a novel framework that leverages a neural network to predict the best dataset combinations. The framework iteratively refines the selection, greatly improving efficiency, while being model-, dataset-, and domain-independent. Through experiments on 12 biomedical datasets across four tasks{---}named entity recognition, relation extraction, event extraction, and text classification{---}we demonstrate that our approach effectively identifies better combinations, even for tasks that may seem unpromising from a human perspective. This verifies that our framework provides a promising solution for maximizing MTL potential."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhan-zhang-2025-towards">
<titleInfo>
<title>Towards Better Multi-task Learning: A Framework for Optimizing Dataset Combinations in Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zaifu</namePart>
<namePart type="family">Zhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Zhang</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>Findings of the Association for Computational Linguistics: NAACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</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">979-8-89176-195-7</identifier>
</relatedItem>
<abstract>To efficiently select optimal dataset combinations for enhancing multi-task learning (MTL) performance in large language models, we proposed a novel framework that leverages a neural network to predict the best dataset combinations. The framework iteratively refines the selection, greatly improving efficiency, while being model-, dataset-, and domain-independent. Through experiments on 12 biomedical datasets across four tasks—named entity recognition, relation extraction, event extraction, and text classification—we demonstrate that our approach effectively identifies better combinations, even for tasks that may seem unpromising from a human perspective. This verifies that our framework provides a promising solution for maximizing MTL potential.</abstract>
<identifier type="citekey">zhan-zhang-2025-towards</identifier>
<identifier type="doi">10.18653/v1/2025.findings-naacl.297</identifier>
<location>
<url>https://aclanthology.org/2025.findings-naacl.297/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>5373</start>
<end>5386</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Better Multi-task Learning: A Framework for Optimizing Dataset Combinations in Large Language Models
%A Zhan, Zaifu
%A Zhang, Rui
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F zhan-zhang-2025-towards
%X To efficiently select optimal dataset combinations for enhancing multi-task learning (MTL) performance in large language models, we proposed a novel framework that leverages a neural network to predict the best dataset combinations. The framework iteratively refines the selection, greatly improving efficiency, while being model-, dataset-, and domain-independent. Through experiments on 12 biomedical datasets across four tasks—named entity recognition, relation extraction, event extraction, and text classification—we demonstrate that our approach effectively identifies better combinations, even for tasks that may seem unpromising from a human perspective. This verifies that our framework provides a promising solution for maximizing MTL potential.
%R 10.18653/v1/2025.findings-naacl.297
%U https://aclanthology.org/2025.findings-naacl.297/
%U https://doi.org/10.18653/v1/2025.findings-naacl.297
%P 5373-5386
Markdown (Informal)
[Towards Better Multi-task Learning: A Framework for Optimizing Dataset Combinations in Large Language Models](https://aclanthology.org/2025.findings-naacl.297/) (Zhan & Zhang, Findings 2025)
ACL