@inproceedings{zhang-etal-2025-law,
    title = "The Law of Knowledge Overshadowing: Towards Understanding, Predicting and Preventing {LLM} Hallucination",
    author = "Zhang, Yuji  and
      Li, Sha  and
      Qian, Cheng  and
      Liu, Jiateng  and
      Yu, Pengfei  and
      Han, Chi  and
      Fung, Yi R.  and
      McKeown, Kathleen  and
      Zhai, ChengXiang  and
      Li, Manling  and
      Ji, Heng",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.findings-acl.1199/",
    pages = "23340--23358",
    ISBN = "979-8-89176-256-5",
    abstract = "Hallucination is a persistent challenge in large language models (LLMs), where even with rigorous quality control, models often generate distorted facts. This paradox, in which error generation continues despite high-quality training data, calls for a deeper understanding of the underlying LLM mechanisms. To address it, we propose a novel concept: knowledge overshadowing, where model{'}s dominant knowledge can obscure less prominent knowledge during text generation, causing the model to fabricate inaccurate details. Building on this idea, we introduce a novel framework to quantify factual hallucinations by modeling knowledge overshadowing. Central to our approach is the log-linear law, which predicts that the rate of factual hallucination increases linearly with the logarithmic scale of (1) Knowledge Popularity, (2) Knowledge Length, and (3) Model Size. The law provides a means to preemptively quantify hallucinations, offering foresight into their occurrence even before model training or inference. Built on overshadowing effect, we propose a new decoding strategy CoDa, to mitigate hallucinations, which notably enhance model factuality on Overshadow (27.9{\%}), MemoTrap (13.1{\%}) and NQ-Swap (18.3{\%}). Our findings not only deepen understandings of the underlying mechanisms behind hallucinations but also provide actionable insights for developing more predictable and controllable language models."
}