@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://preview.aclanthology.org/ingest-acl/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."
}