@inproceedings{hu-etal-2026-multi,
title = "Multi-Task Representation Alignment on Language Understanding: A Mutual Information Perspective",
author = "Hu, Dou and
Wei, Lingwei and
Xiao, Hongjiang and
Hu, Songlin and
Zhang, Yuan",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.2120/",
pages = "45722--45740",
ISBN = "979-8-89176-390-6",
abstract = "Multi-task learning (MTL) enables joint learning over multiple tasks based on shared representations, but suffers from task interference issue during optimization. Existing works mainly focus on task balancing or probabilistic modeling but fail to address the issue since they struggle to learn sufficient representations for all target tasks. To address this, we propose a multi-task representation alignment (MTRA) framework to achieve task-specific alignment and self-alignment on the shared representations from a mutual information perspective. MTRA ensures that the learned representations contain task-relevant features while mitigating the negative effects of task-irrelevant features. First, we design a task-specific alignment objective to align the shared representations and task-specific representations with the expected targets of all tasks via information maximization. Besides, we design a self-alignment objective to eliminate task-irrelevant features via conditional information minimization. Experiments on two multi-task language benchmarks show that MTRA outperforms 13 representative MTL methods under the same settings, particularly under label-noisy and data-constrained conditions. Further analysis shows that the learned shared representations exhibit sufficient task informativeness and superior alignment properties."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hu-etal-2026-multi">
<titleInfo>
<title>Multi-Task Representation Alignment on Language Understanding: A Mutual Information Perspective</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dou</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lingwei</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongjiang</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Songlin</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Multi-task learning (MTL) enables joint learning over multiple tasks based on shared representations, but suffers from task interference issue during optimization. Existing works mainly focus on task balancing or probabilistic modeling but fail to address the issue since they struggle to learn sufficient representations for all target tasks. To address this, we propose a multi-task representation alignment (MTRA) framework to achieve task-specific alignment and self-alignment on the shared representations from a mutual information perspective. MTRA ensures that the learned representations contain task-relevant features while mitigating the negative effects of task-irrelevant features. First, we design a task-specific alignment objective to align the shared representations and task-specific representations with the expected targets of all tasks via information maximization. Besides, we design a self-alignment objective to eliminate task-irrelevant features via conditional information minimization. Experiments on two multi-task language benchmarks show that MTRA outperforms 13 representative MTL methods under the same settings, particularly under label-noisy and data-constrained conditions. Further analysis shows that the learned shared representations exhibit sufficient task informativeness and superior alignment properties.</abstract>
<identifier type="citekey">hu-etal-2026-multi</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.2120/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>45722</start>
<end>45740</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-Task Representation Alignment on Language Understanding: A Mutual Information Perspective
%A Hu, Dou
%A Wei, Lingwei
%A Xiao, Hongjiang
%A Hu, Songlin
%A Zhang, Yuan
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F hu-etal-2026-multi
%X Multi-task learning (MTL) enables joint learning over multiple tasks based on shared representations, but suffers from task interference issue during optimization. Existing works mainly focus on task balancing or probabilistic modeling but fail to address the issue since they struggle to learn sufficient representations for all target tasks. To address this, we propose a multi-task representation alignment (MTRA) framework to achieve task-specific alignment and self-alignment on the shared representations from a mutual information perspective. MTRA ensures that the learned representations contain task-relevant features while mitigating the negative effects of task-irrelevant features. First, we design a task-specific alignment objective to align the shared representations and task-specific representations with the expected targets of all tasks via information maximization. Besides, we design a self-alignment objective to eliminate task-irrelevant features via conditional information minimization. Experiments on two multi-task language benchmarks show that MTRA outperforms 13 representative MTL methods under the same settings, particularly under label-noisy and data-constrained conditions. Further analysis shows that the learned shared representations exhibit sufficient task informativeness and superior alignment properties.
%U https://aclanthology.org/2026.acl-long.2120/
%P 45722-45740
Markdown (Informal)
[Multi-Task Representation Alignment on Language Understanding: A Mutual Information Perspective](https://aclanthology.org/2026.acl-long.2120/) (Hu et al., ACL 2026)
ACL