@inproceedings{wu-etal-2026-yue,
title = "{YUE}-{PUB}: A {C}antonese Pragmatic Understanding Benchmark",
author = "Wu, Chengyan and
Gong, Ziwei and
Chen, Jinzhi and
Su, Mengmeng and
Xue, Yun and
Ma, Bolei",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-aacl.1/",
pages = "1--22",
ISBN = "979-8-89176-444-6",
abstract = "Pragmatic understanding remains a fundamental challenge in natural language processing, particularly for underrepresented languages such as Cantonese. To alleviate the scarcity of resources in this area, we introduce YUE-PUB, the first large-scale pragmatic understanding benchmark for Cantonese. Constructed from the PUB dataset through automatic translation with human verification for quality assurance, YUE-PUB covers three core pragmatic phenomena: Implicature, Presupposition, and Reference. We conduct systematic experiments across multiple baseline models to evaluate their performance under several cross-lingual transfer settings, compare models with and without pragmatic topic awareness, and further analyze their sensitivity to different pragmatic phenomena as well as their Chain-of-Thought (CoT) reasoning behavior. Experimental results show that current large language models still exhibit substantial limitations in Cantonese pragmatic understanding, underscoring the value of YUE-PUB as an important resource for advancing pragmatic reasoning research in low-resource languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2026-yue">
<titleInfo>
<title>YUE-PUB: A Cantonese Pragmatic Understanding Benchmark</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengyan</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziwei</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinzhi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengmeng</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bolei</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</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">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-444-6</identifier>
</relatedItem>
<abstract>Pragmatic understanding remains a fundamental challenge in natural language processing, particularly for underrepresented languages such as Cantonese. To alleviate the scarcity of resources in this area, we introduce YUE-PUB, the first large-scale pragmatic understanding benchmark for Cantonese. Constructed from the PUB dataset through automatic translation with human verification for quality assurance, YUE-PUB covers three core pragmatic phenomena: Implicature, Presupposition, and Reference. We conduct systematic experiments across multiple baseline models to evaluate their performance under several cross-lingual transfer settings, compare models with and without pragmatic topic awareness, and further analyze their sensitivity to different pragmatic phenomena as well as their Chain-of-Thought (CoT) reasoning behavior. Experimental results show that current large language models still exhibit substantial limitations in Cantonese pragmatic understanding, underscoring the value of YUE-PUB as an important resource for advancing pragmatic reasoning research in low-resource languages.</abstract>
<identifier type="citekey">wu-etal-2026-yue</identifier>
<location>
<url>https://aclanthology.org/2026.findings-aacl.1/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>1</start>
<end>22</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T YUE-PUB: A Cantonese Pragmatic Understanding Benchmark
%A Wu, Chengyan
%A Gong, Ziwei
%A Chen, Jinzhi
%A Su, Mengmeng
%A Xue, Yun
%A Ma, Bolei
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F wu-etal-2026-yue
%X Pragmatic understanding remains a fundamental challenge in natural language processing, particularly for underrepresented languages such as Cantonese. To alleviate the scarcity of resources in this area, we introduce YUE-PUB, the first large-scale pragmatic understanding benchmark for Cantonese. Constructed from the PUB dataset through automatic translation with human verification for quality assurance, YUE-PUB covers three core pragmatic phenomena: Implicature, Presupposition, and Reference. We conduct systematic experiments across multiple baseline models to evaluate their performance under several cross-lingual transfer settings, compare models with and without pragmatic topic awareness, and further analyze their sensitivity to different pragmatic phenomena as well as their Chain-of-Thought (CoT) reasoning behavior. Experimental results show that current large language models still exhibit substantial limitations in Cantonese pragmatic understanding, underscoring the value of YUE-PUB as an important resource for advancing pragmatic reasoning research in low-resource languages.
%U https://aclanthology.org/2026.findings-aacl.1/
%P 1-22
Markdown (Informal)
[YUE-PUB: A Cantonese Pragmatic Understanding Benchmark](https://aclanthology.org/2026.findings-aacl.1/) (Wu et al., Findings 2026)
ACL
- Chengyan Wu, Ziwei Gong, Jinzhi Chen, Mengmeng Su, Yun Xue, and Bolei Ma. 2026. YUE-PUB: A Cantonese Pragmatic Understanding Benchmark. In Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026, pages 1–22, Hengqin, China. Association for Computational Linguistics.