@inproceedings{chen-etal-2026-dynamic-pmi,
    title = "Dynamic {PMI}-Guided Contrastive Decoding Reduces Hallucination in Large Language Models: A Unified Framework of Fine-Grained Input Transformations",
    author = "Chen, Dongsheng  and
      Zhu, Yingqi  and
      Zhang, Xingyue  and
      Zhou, Wenqing  and
      Li, Lei",
    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.1212/",
    pages = "24223--24235",
    ISBN = "979-8-89176-395-1",
    abstract = "Despite the remarkable generation capabilities demonstrated by large language models (LLMs), the issue of hallucination remains a critical challenge. This is largely attributed to the models' tendency to fit spurious dependencies in pre-training data rather than underlying causal logic. To address this, from an information-theoretic perspective, this paper proposes a unified contrastive decoding framework based on dynamic pointwise mutual information (Dynamic PMI). Under this framework, we design three fine-grained input transformation strategies targeting context, syntax, and semantics to construct dynamic background distributions. These strategies systematically disentangle and suppress spurious dependencies induced by context priors, lexical co-occurrences, and syntactic structures, thereby guiding the model to prioritize underlying causal logic. Experiments on extensive discriminative and generative benchmarks demonstrate that our method significantly improves the model{'}s factuality and reasoning robustness. Notably, despite employing a single-model architecture, our framework surpasses state-of-the-art dual-model strategies while maintaining high computational efficiency. Furthermore, the framework exhibits strong cross-model generalizability and effectively alleviates the over-refusal tendency in open-ended generation."
}