@inproceedings{ghattas-etal-2025-pruning,
title = "On Pruning State-Space {LLM}s",
author = "Ghattas, Tamer and
Hassid, Michael and
Schwartz, Roy",
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.950/",
pages = "18811--18825",
ISBN = "979-8-89176-332-6",
abstract = "Recent work proposed state-space models (SSMs) as an efficient alternative to transformer-based LLMs. Can these models be pruned to further reduce their computation costs? We adapt several pruning methods to the SSM structure, and apply them to four SSM-based LLMs across multiple tasks. We find that such models are quite robust to some pruning methods (e.g., WANDA), while using other methods lead to fast performance degradation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ghattas-etal-2025-pruning">
<titleInfo>
<title>On Pruning State-Space LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Ghattas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Hassid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roy</namePart>
<namePart type="family">Schwartz</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>Recent work proposed state-space models (SSMs) as an efficient alternative to transformer-based LLMs. Can these models be pruned to further reduce their computation costs? We adapt several pruning methods to the SSM structure, and apply them to four SSM-based LLMs across multiple tasks. We find that such models are quite robust to some pruning methods (e.g., WANDA), while using other methods lead to fast performance degradation.</abstract>
<identifier type="citekey">ghattas-etal-2025-pruning</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.950/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>18811</start>
<end>18825</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On Pruning State-Space LLMs
%A Ghattas, Tamer
%A Hassid, Michael
%A Schwartz, Roy
%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 ghattas-etal-2025-pruning
%X Recent work proposed state-space models (SSMs) as an efficient alternative to transformer-based LLMs. Can these models be pruned to further reduce their computation costs? We adapt several pruning methods to the SSM structure, and apply them to four SSM-based LLMs across multiple tasks. We find that such models are quite robust to some pruning methods (e.g., WANDA), while using other methods lead to fast performance degradation.
%U https://aclanthology.org/2025.emnlp-main.950/
%P 18811-18825
Markdown (Informal)
[On Pruning State-Space LLMs](https://aclanthology.org/2025.emnlp-main.950/) (Ghattas et al., EMNLP 2025)
ACL
- Tamer Ghattas, Michael Hassid, and Roy Schwartz. 2025. On Pruning State-Space LLMs. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 18811–18825, Suzhou, China. Association for Computational Linguistics.