@inproceedings{liu-etal-2026-parameter,
title = "Parameter-Efficient Routed Fine-Tuning: Mixture-of-Experts Demands Mixture of Adaptation Modules",
author = "Liu, Yilun and
Ma, Yunpu and
Lu, Yuetian and
Chen, Shuo and
Ding, Zifeng and
Tresp, Volker",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-eacl.232/",
pages = "4439--4457",
ISBN = "979-8-89176-386-9",
abstract = "Mixture-of-Experts (MoE) benefits from a dynamic routing mechanism among their specialized experts, which existing Parameter- Efficient Fine-Tuning (PEFT) strategies often fail to leverage. This motivates us to investigate whether adaptation modules themselves should incorporate routing mechanisms to align with MoE{'}s multi-expert architecture. We analyze dynamics of core components when applying PEFT to MoE language models, and examine how different routing strategies affect adaptation effectiveness. Extensive experiments adapting OLMoE-1B-7B and Mixtral-8{\texttimes}7B on various commonsense and math reasoning tasks validate the performance and efficiency of our routed approach. We identify optimal configurations for different scenarios and provide empirical analyses with practical insights to facilitate better PEFT and MoE applications."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-parameter">
<titleInfo>
<title>Parameter-Efficient Routed Fine-Tuning: Mixture-of-Experts Demands Mixture of Adaptation Modules</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yilun</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunpu</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuetian</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuo</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zifeng</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Volker</namePart>
<namePart type="family">Tresp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-386-9</identifier>
</relatedItem>
<abstract>Mixture-of-Experts (MoE) benefits from a dynamic routing mechanism among their specialized experts, which existing Parameter- Efficient Fine-Tuning (PEFT) strategies often fail to leverage. This motivates us to investigate whether adaptation modules themselves should incorporate routing mechanisms to align with MoE’s multi-expert architecture. We analyze dynamics of core components when applying PEFT to MoE language models, and examine how different routing strategies affect adaptation effectiveness. Extensive experiments adapting OLMoE-1B-7B and Mixtral-8×7B on various commonsense and math reasoning tasks validate the performance and efficiency of our routed approach. We identify optimal configurations for different scenarios and provide empirical analyses with practical insights to facilitate better PEFT and MoE applications.</abstract>
<identifier type="citekey">liu-etal-2026-parameter</identifier>
<location>
<url>https://aclanthology.org/2026.findings-eacl.232/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>4439</start>
<end>4457</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Parameter-Efficient Routed Fine-Tuning: Mixture-of-Experts Demands Mixture of Adaptation Modules
%A Liu, Yilun
%A Ma, Yunpu
%A Lu, Yuetian
%A Chen, Shuo
%A Ding, Zifeng
%A Tresp, Volker
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Findings of the Association for Computational Linguistics: EACL 2026
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-386-9
%F liu-etal-2026-parameter
%X Mixture-of-Experts (MoE) benefits from a dynamic routing mechanism among their specialized experts, which existing Parameter- Efficient Fine-Tuning (PEFT) strategies often fail to leverage. This motivates us to investigate whether adaptation modules themselves should incorporate routing mechanisms to align with MoE’s multi-expert architecture. We analyze dynamics of core components when applying PEFT to MoE language models, and examine how different routing strategies affect adaptation effectiveness. Extensive experiments adapting OLMoE-1B-7B and Mixtral-8×7B on various commonsense and math reasoning tasks validate the performance and efficiency of our routed approach. We identify optimal configurations for different scenarios and provide empirical analyses with practical insights to facilitate better PEFT and MoE applications.
%U https://aclanthology.org/2026.findings-eacl.232/
%P 4439-4457
Markdown (Informal)
[Parameter-Efficient Routed Fine-Tuning: Mixture-of-Experts Demands Mixture of Adaptation Modules](https://aclanthology.org/2026.findings-eacl.232/) (Liu et al., Findings 2026)
ACL