@inproceedings{shi-etal-2026-improve,
title = "How to Improve {LLM}s' Performance on Specific Languages: A Perspective on {LLM}-Derived Language Similarity",
author = "Shi, Xinhe and
Zeng, Qingcheng and
Xuan, Weihao and
Zhu, Linchao",
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.691/",
pages = "15139--15164",
ISBN = "979-8-89176-390-6",
abstract = "Large language models (LLMs) exhibit uneven performance across languages. In language-specific applications, practitioners often rely on target-language corpora or cross-lingual transfer to achieve better performance. However, traditional linguistic typology, commonly used as a transfer language selection strategy in previous studies, may not align with LLM{'}s perception of language similarity. This work proposes **LLM-based language similarity** as a novel perspective for selecting effective fine-tuning languages. We construct a framework to quantify the similarity within each language pair through both the lenses of **language-specific performance patterns** and **cross-lingual transferability**, ultimately deriving three similarity score matrices. Moreover, we observe a counter-intuitive phenomenon: **super-additive transfer effect**, where fine-tuning on a certain language yields higher performance than fine-tuning directly on the target language. Additionally, due to the absence of an existing dataset meeting our experimental requirements, we construct and release **M4CQ-Pro** dataset, which features domain-diverse distribution of **135** tasks and content consistency across **31** languages (including over 20 medium- and low-resource languages), with 61518 manually reviewed high-quality questions per language. We evaluate our approach on representative multilingual LLMs and results show that all three LLM-based similarity measures effectively guide fine-tuning language selection, outperforming traditional linguistic similarity, with the integrated measure achieving the best results. Our approach provides not only **a novel perspective on language similarity**, but also **practical baselines for selecting fine-tuning languages**."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shi-etal-2026-improve">
<titleInfo>
<title>How to Improve LLMs’ Performance on Specific Languages: A Perspective on LLM-Derived Language Similarity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinhe</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingcheng</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weihao</namePart>
<namePart type="family">Xuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linchao</namePart>
<namePart type="family">Zhu</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>Large language models (LLMs) exhibit uneven performance across languages. In language-specific applications, practitioners often rely on target-language corpora or cross-lingual transfer to achieve better performance. However, traditional linguistic typology, commonly used as a transfer language selection strategy in previous studies, may not align with LLM’s perception of language similarity. This work proposes **LLM-based language similarity** as a novel perspective for selecting effective fine-tuning languages. We construct a framework to quantify the similarity within each language pair through both the lenses of **language-specific performance patterns** and **cross-lingual transferability**, ultimately deriving three similarity score matrices. Moreover, we observe a counter-intuitive phenomenon: **super-additive transfer effect**, where fine-tuning on a certain language yields higher performance than fine-tuning directly on the target language. Additionally, due to the absence of an existing dataset meeting our experimental requirements, we construct and release **M4CQ-Pro** dataset, which features domain-diverse distribution of **135** tasks and content consistency across **31** languages (including over 20 medium- and low-resource languages), with 61518 manually reviewed high-quality questions per language. We evaluate our approach on representative multilingual LLMs and results show that all three LLM-based similarity measures effectively guide fine-tuning language selection, outperforming traditional linguistic similarity, with the integrated measure achieving the best results. Our approach provides not only **a novel perspective on language similarity**, but also **practical baselines for selecting fine-tuning languages**.</abstract>
<identifier type="citekey">shi-etal-2026-improve</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.691/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>15139</start>
<end>15164</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How to Improve LLMs’ Performance on Specific Languages: A Perspective on LLM-Derived Language Similarity
%A Shi, Xinhe
%A Zeng, Qingcheng
%A Xuan, Weihao
%A Zhu, Linchao
%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 shi-etal-2026-improve
%X Large language models (LLMs) exhibit uneven performance across languages. In language-specific applications, practitioners often rely on target-language corpora or cross-lingual transfer to achieve better performance. However, traditional linguistic typology, commonly used as a transfer language selection strategy in previous studies, may not align with LLM’s perception of language similarity. This work proposes **LLM-based language similarity** as a novel perspective for selecting effective fine-tuning languages. We construct a framework to quantify the similarity within each language pair through both the lenses of **language-specific performance patterns** and **cross-lingual transferability**, ultimately deriving three similarity score matrices. Moreover, we observe a counter-intuitive phenomenon: **super-additive transfer effect**, where fine-tuning on a certain language yields higher performance than fine-tuning directly on the target language. Additionally, due to the absence of an existing dataset meeting our experimental requirements, we construct and release **M4CQ-Pro** dataset, which features domain-diverse distribution of **135** tasks and content consistency across **31** languages (including over 20 medium- and low-resource languages), with 61518 manually reviewed high-quality questions per language. We evaluate our approach on representative multilingual LLMs and results show that all three LLM-based similarity measures effectively guide fine-tuning language selection, outperforming traditional linguistic similarity, with the integrated measure achieving the best results. Our approach provides not only **a novel perspective on language similarity**, but also **practical baselines for selecting fine-tuning languages**.
%U https://aclanthology.org/2026.acl-long.691/
%P 15139-15164
Markdown (Informal)
[How to Improve LLMs’ Performance on Specific Languages: A Perspective on LLM-Derived Language Similarity](https://aclanthology.org/2026.acl-long.691/) (Shi et al., ACL 2026)
ACL