@inproceedings{liu-etal-2026-penetrating,
title = "Penetrating Linguistic Disguises: A Slang-aware Label-Aligned Framework for Fine-Grained Toxicity Extraction in {C}hinese Hate Speech Detection",
author = "Liu, Wei and
Chen, Xiaoliang and
Miao, Duoqian and
Gu, Xu and
Li, Xianyong and
Du, Yajun",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1061/",
pages = "21111--21123",
ISBN = "979-8-89176-395-1",
abstract = "Flexible word boundaries and linguistic obfuscation, particularly slang, challenge precise span-level hate speech detection in Chinese. While benchmarks such as STATE ToxiCN demand the exact extraction of Target-Argument-Hateful-Group quadruples, generative Large Language Models (LLMs) often fail strict boundary constraints. In contrast, discriminative 2D Grid Tagging methods frequently encounter label collisions. To resolve these problems, this study presents a Slang-aware Label-Aligned Framework. A Structural-Semantic Lexicon Fusion (SSLF) module reduces ambiguity by mapping obscure slang to explicit hate semantics. Additionally, the proposed Label-Disentangled Volumetric Tagging (LDVT) projects token interactions into a volumetric space. LDVT uses task-specific branches and dedicated label channels to structurally mitigate feature interference. This approach removes label collisions without heuristic post-processing. Empirical outcomes on STATE ToxiCN indicate a Hard-F1 of 30.09{\%}. This performance is 5.82{\%} higher than the best fine-tuned LLM baseline and confirms the method is effective for exact-match extraction."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-penetrating">
<titleInfo>
<title>Penetrating Linguistic Disguises: A Slang-aware Label-Aligned Framework for Fine-Grained Toxicity Extraction in Chinese Hate Speech Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoliang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Duoqian</namePart>
<namePart type="family">Miao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianyong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yajun</namePart>
<namePart type="family">Du</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>Findings of the Association for Computational Linguistics: ACL 2026</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">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Flexible word boundaries and linguistic obfuscation, particularly slang, challenge precise span-level hate speech detection in Chinese. While benchmarks such as STATE ToxiCN demand the exact extraction of Target-Argument-Hateful-Group quadruples, generative Large Language Models (LLMs) often fail strict boundary constraints. In contrast, discriminative 2D Grid Tagging methods frequently encounter label collisions. To resolve these problems, this study presents a Slang-aware Label-Aligned Framework. A Structural-Semantic Lexicon Fusion (SSLF) module reduces ambiguity by mapping obscure slang to explicit hate semantics. Additionally, the proposed Label-Disentangled Volumetric Tagging (LDVT) projects token interactions into a volumetric space. LDVT uses task-specific branches and dedicated label channels to structurally mitigate feature interference. This approach removes label collisions without heuristic post-processing. Empirical outcomes on STATE ToxiCN indicate a Hard-F1 of 30.09%. This performance is 5.82% higher than the best fine-tuned LLM baseline and confirms the method is effective for exact-match extraction.</abstract>
<identifier type="citekey">liu-etal-2026-penetrating</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1061/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>21111</start>
<end>21123</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Penetrating Linguistic Disguises: A Slang-aware Label-Aligned Framework for Fine-Grained Toxicity Extraction in Chinese Hate Speech Detection
%A Liu, Wei
%A Chen, Xiaoliang
%A Miao, Duoqian
%A Gu, Xu
%A Li, Xianyong
%A Du, Yajun
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F liu-etal-2026-penetrating
%X Flexible word boundaries and linguistic obfuscation, particularly slang, challenge precise span-level hate speech detection in Chinese. While benchmarks such as STATE ToxiCN demand the exact extraction of Target-Argument-Hateful-Group quadruples, generative Large Language Models (LLMs) often fail strict boundary constraints. In contrast, discriminative 2D Grid Tagging methods frequently encounter label collisions. To resolve these problems, this study presents a Slang-aware Label-Aligned Framework. A Structural-Semantic Lexicon Fusion (SSLF) module reduces ambiguity by mapping obscure slang to explicit hate semantics. Additionally, the proposed Label-Disentangled Volumetric Tagging (LDVT) projects token interactions into a volumetric space. LDVT uses task-specific branches and dedicated label channels to structurally mitigate feature interference. This approach removes label collisions without heuristic post-processing. Empirical outcomes on STATE ToxiCN indicate a Hard-F1 of 30.09%. This performance is 5.82% higher than the best fine-tuned LLM baseline and confirms the method is effective for exact-match extraction.
%U https://aclanthology.org/2026.findings-acl.1061/
%P 21111-21123
Markdown (Informal)
[Penetrating Linguistic Disguises: A Slang-aware Label-Aligned Framework for Fine-Grained Toxicity Extraction in Chinese Hate Speech Detection](https://aclanthology.org/2026.findings-acl.1061/) (Liu et al., Findings 2026)
ACL