@inproceedings{yang-etal-2026-lasa,
    title = "{LASA}: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for {LLM} Safety",
    author = "Yang, Junxiao  and
      Liu, Haoran  and
      Tu, Jinzhe  and
      Cheng, Jiale  and
      Zhang, Zhexin  and
      Cui, Shiyao  and
      Weng, Jiaqi  and
      Tao, Jialing  and
      Xue, Hui  and
      Wang, Hongning  and
      Qiu, Han  and
      Huang, Minlie",
    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://preview.aclanthology.org/ingest-acl/2026.acl-long.1913/",
    pages = "41238--41259",
    ISBN = "979-8-89176-390-6",
    abstract = "Large language models (LLMs) have demonstrated better safety performance in high-resource languages than in low-resource languages. We attribute this issue as a mismatch gap between language-agnostic semantic understanding ability and language dominant safety alignment biased toward high-resource languages. Based on above insights, we empirically identify the semantic bottleneck in LLMs: intermediate layers in which the geometry of model representations is governed primarily by shared semantic content rather than language identity. Then, we propose Language-Agnostic Semantic Alignment (LASA), which anchors safety alignment directly in semantic bottlenecks. Experiments show that LASA substantially improves safety across all languages: average attack success rate (ASR) drops from 24.7{\%} to 2.8{\%} on LLaMA-3.1-8B-Instruct and remains within 3{--}4{\%} across Qwen2.5 and Qwen3 Instruct models (7B{--}32B). Besides, our analysis and method offer a representation-level perspective on LLM safety, suggesting that safety alignment requires anchoring safety understanding not in surface text, but in the model{'}s language-agnostic semantic space."
}