@inproceedings{xing-etal-2025-unveiling,
title = "Unveiling the Linguistic Acceptability Judgments of Large Language Models in Multilingual Contexts",
author = "Xing, Fuyu and
Huang, Haoyu and
Mo, Dawei and
Yang, Xinzhuo and
Gao, Zixuan and
Wang, Wei and
Wang, Zimu and
Zhang, Haiyang",
editor = "Sun, Maosong and
Duan, Peiyong and
Liu, Zhiyuan and
Xu, Ruifeng and
Sun, Weiwei",
booktitle = "Proceedings of the 24th {C}hina National Conference on Computational Linguistics ({CCL} 2025)",
month = aug,
year = "2025",
address = "Jinan, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2025.ccl-1.65/",
pages = "852--863",
abstract = "``Linguistic acceptability judgments are essential for evaluating how language models internalize human-like grammatical knowledge. Though some studies have evaluated large language mod-els (LLMs) in this context, existing research lacks systematic exploration of diverse learning paradigms in a multilingual setting. In this paper, we present the first multilingual evaluation of LLMs across four languages (English, Chinese, Japanese, and Russian) in the field of linguistic acceptability. Our evaluation spans both general-purpose (i.e., GPT-4o, GPT-4o mini,DeepSeek-V3, GLM-4-32B, and the Qwen series) and reasoning-oriented (QwQ-32B-Preview and DeepSeek-R1-32B) models under zero-shot and monolingual, cross-lingual and multilingual fine-tuning settings, with comparisons to pre-trained language model (PLM) baselines. Our analysis highlights the strong generalizability of large-scale LLMs through zero-shot prompting, the challenges of fine-tuning small-sized LLMs with skewed training data, the effectiveness of multilingual fine-tuning for low-resource languages, the scaling law exhibited on the task, and the limitation of reasoning-oriented models on the task, even when ``aha moments'' occur during the reasoning process.''"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xing-etal-2025-unveiling">
<titleInfo>
<title>Unveiling the Linguistic Acceptability Judgments of Large Language Models in Multilingual Contexts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fuyu</namePart>
<namePart type="family">Xing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haoyu</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dawei</namePart>
<namePart type="family">Mo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinzhuo</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zixuan</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zimu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haiyang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th China National Conference on Computational Linguistics (CCL 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peiyong</namePart>
<namePart type="family">Duan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiwei</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Jinan, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>“Linguistic acceptability judgments are essential for evaluating how language models internalize human-like grammatical knowledge. Though some studies have evaluated large language mod-els (LLMs) in this context, existing research lacks systematic exploration of diverse learning paradigms in a multilingual setting. In this paper, we present the first multilingual evaluation of LLMs across four languages (English, Chinese, Japanese, and Russian) in the field of linguistic acceptability. Our evaluation spans both general-purpose (i.e., GPT-4o, GPT-4o mini,DeepSeek-V3, GLM-4-32B, and the Qwen series) and reasoning-oriented (QwQ-32B-Preview and DeepSeek-R1-32B) models under zero-shot and monolingual, cross-lingual and multilingual fine-tuning settings, with comparisons to pre-trained language model (PLM) baselines. Our analysis highlights the strong generalizability of large-scale LLMs through zero-shot prompting, the challenges of fine-tuning small-sized LLMs with skewed training data, the effectiveness of multilingual fine-tuning for low-resource languages, the scaling law exhibited on the task, and the limitation of reasoning-oriented models on the task, even when “aha moments” occur during the reasoning process.”</abstract>
<identifier type="citekey">xing-etal-2025-unveiling</identifier>
<location>
<url>https://aclanthology.org/2025.ccl-1.65/</url>
</location>
<part>
<date>2025-08</date>
<extent unit="page">
<start>852</start>
<end>863</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unveiling the Linguistic Acceptability Judgments of Large Language Models in Multilingual Contexts
%A Xing, Fuyu
%A Huang, Haoyu
%A Mo, Dawei
%A Yang, Xinzhuo
%A Gao, Zixuan
%A Wang, Wei
%A Wang, Zimu
%A Zhang, Haiyang
%Y Sun, Maosong
%Y Duan, Peiyong
%Y Liu, Zhiyuan
%Y Xu, Ruifeng
%Y Sun, Weiwei
%S Proceedings of the 24th China National Conference on Computational Linguistics (CCL 2025)
%D 2025
%8 August
%I Chinese Information Processing Society of China
%C Jinan, China
%F xing-etal-2025-unveiling
%X “Linguistic acceptability judgments are essential for evaluating how language models internalize human-like grammatical knowledge. Though some studies have evaluated large language mod-els (LLMs) in this context, existing research lacks systematic exploration of diverse learning paradigms in a multilingual setting. In this paper, we present the first multilingual evaluation of LLMs across four languages (English, Chinese, Japanese, and Russian) in the field of linguistic acceptability. Our evaluation spans both general-purpose (i.e., GPT-4o, GPT-4o mini,DeepSeek-V3, GLM-4-32B, and the Qwen series) and reasoning-oriented (QwQ-32B-Preview and DeepSeek-R1-32B) models under zero-shot and monolingual, cross-lingual and multilingual fine-tuning settings, with comparisons to pre-trained language model (PLM) baselines. Our analysis highlights the strong generalizability of large-scale LLMs through zero-shot prompting, the challenges of fine-tuning small-sized LLMs with skewed training data, the effectiveness of multilingual fine-tuning for low-resource languages, the scaling law exhibited on the task, and the limitation of reasoning-oriented models on the task, even when “aha moments” occur during the reasoning process.”
%U https://aclanthology.org/2025.ccl-1.65/
%P 852-863
Markdown (Informal)
[Unveiling the Linguistic Acceptability Judgments of Large Language Models in Multilingual Contexts](https://aclanthology.org/2025.ccl-1.65/) (Xing et al., CCL 2025)
ACL
- Fuyu Xing, Haoyu Huang, Dawei Mo, Xinzhuo Yang, Zixuan Gao, Wei Wang, Zimu Wang, and Haiyang Zhang. 2025. Unveiling the Linguistic Acceptability Judgments of Large Language Models in Multilingual Contexts. In Proceedings of the 24th China National Conference on Computational Linguistics (CCL 2025), pages 852–863, Jinan, China. Chinese Information Processing Society of China.