@inproceedings{elshabrawy-etal-2025-statement,
title = "Statement-Tuning Enables Efficient Cross-lingual Generalization in Encoder-only Models",
author = "Elshabrawy, Ahmed and
Nguyen, Thanh-Nhi and
Kang, Yeeun and
Feng, Lihan and
Jain, Annant and
Shaikh, Faadil Abdullah and
Mansurov, Jonibek and
Imam, Mohamed Fazli Mohamed and
Ortiz-Barajas, Jesus-German and
Chevi, Rendi and
Aji, Alham Fikri",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.835/",
doi = "10.18653/v1/2025.findings-acl.835",
pages = "16226--16248",
ISBN = "979-8-89176-256-5",
abstract = "Large Language Models (LLMs) excel in zero-shot and few-shot tasks, but achieving similar performance with encoder-only models like BERT and RoBERTa has been challenging due to their architecture. However, encoders offer advantages such as lower computational and memory costs. Recent work adapts them for zero-shot generalization using Statement Tuning, which reformulates tasks into finite templates. We extend this approach to multilingual NLP, exploring whether encoders can achieve zero-shot cross-lingual generalization and serve as efficient alternatives to memory-intensive LLMs for low-resource languages. Our results show that state-of-the-art encoder models generalize well across languages, rivaling multilingual LLMs while being more efficient. We also analyze multilingual Statement Tuning dataset design, efficiency gains, and language-specific generalization, contributing to more inclusive and resource-efficient NLP models. We release our code and models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="elshabrawy-etal-2025-statement">
<titleInfo>
<title>Statement-Tuning Enables Efficient Cross-lingual Generalization in Encoder-only Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Elshabrawy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thanh-Nhi</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yeeun</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lihan</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annant</namePart>
<namePart type="family">Jain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Faadil</namePart>
<namePart type="given">Abdullah</namePart>
<namePart type="family">Shaikh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonibek</namePart>
<namePart type="family">Mansurov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="given">Fazli</namePart>
<namePart type="given">Mohamed</namePart>
<namePart type="family">Imam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesus-German</namePart>
<namePart type="family">Ortiz-Barajas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rendi</namePart>
<namePart type="family">Chevi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alham</namePart>
<namePart type="given">Fikri</namePart>
<namePart type="family">Aji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) excel in zero-shot and few-shot tasks, but achieving similar performance with encoder-only models like BERT and RoBERTa has been challenging due to their architecture. However, encoders offer advantages such as lower computational and memory costs. Recent work adapts them for zero-shot generalization using Statement Tuning, which reformulates tasks into finite templates. We extend this approach to multilingual NLP, exploring whether encoders can achieve zero-shot cross-lingual generalization and serve as efficient alternatives to memory-intensive LLMs for low-resource languages. Our results show that state-of-the-art encoder models generalize well across languages, rivaling multilingual LLMs while being more efficient. We also analyze multilingual Statement Tuning dataset design, efficiency gains, and language-specific generalization, contributing to more inclusive and resource-efficient NLP models. We release our code and models.</abstract>
<identifier type="citekey">elshabrawy-etal-2025-statement</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.835</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.835/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>16226</start>
<end>16248</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Statement-Tuning Enables Efficient Cross-lingual Generalization in Encoder-only Models
%A Elshabrawy, Ahmed
%A Nguyen, Thanh-Nhi
%A Kang, Yeeun
%A Feng, Lihan
%A Jain, Annant
%A Shaikh, Faadil Abdullah
%A Mansurov, Jonibek
%A Imam, Mohamed Fazli Mohamed
%A Ortiz-Barajas, Jesus-German
%A Chevi, Rendi
%A Aji, Alham Fikri
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F elshabrawy-etal-2025-statement
%X Large Language Models (LLMs) excel in zero-shot and few-shot tasks, but achieving similar performance with encoder-only models like BERT and RoBERTa has been challenging due to their architecture. However, encoders offer advantages such as lower computational and memory costs. Recent work adapts them for zero-shot generalization using Statement Tuning, which reformulates tasks into finite templates. We extend this approach to multilingual NLP, exploring whether encoders can achieve zero-shot cross-lingual generalization and serve as efficient alternatives to memory-intensive LLMs for low-resource languages. Our results show that state-of-the-art encoder models generalize well across languages, rivaling multilingual LLMs while being more efficient. We also analyze multilingual Statement Tuning dataset design, efficiency gains, and language-specific generalization, contributing to more inclusive and resource-efficient NLP models. We release our code and models.
%R 10.18653/v1/2025.findings-acl.835
%U https://aclanthology.org/2025.findings-acl.835/
%U https://doi.org/10.18653/v1/2025.findings-acl.835
%P 16226-16248
Markdown (Informal)
[Statement-Tuning Enables Efficient Cross-lingual Generalization in Encoder-only Models](https://aclanthology.org/2025.findings-acl.835/) (Elshabrawy et al., Findings 2025)
ACL
- Ahmed Elshabrawy, Thanh-Nhi Nguyen, Yeeun Kang, Lihan Feng, Annant Jain, Faadil Abdullah Shaikh, Jonibek Mansurov, Mohamed Fazli Mohamed Imam, Jesus-German Ortiz-Barajas, Rendi Chevi, and Alham Fikri Aji. 2025. Statement-Tuning Enables Efficient Cross-lingual Generalization in Encoder-only Models. In Findings of the Association for Computational Linguistics: ACL 2025, pages 16226–16248, Vienna, Austria. Association for Computational Linguistics.