ACL 2025finding0 citations

Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models

Yanwen Huang, Yong Zhang, Ning Cheng, Zhitao Li, Shaojun Wang, Jing Xiao

Abstract

Large language models (LLMs) often exhibit Context Faithfulness Hallucinations, where outputs deviate from retrieved information due to incomplete context integration. Our analysis reveals a strong correlation between token-level uncertainty and hallucinations. We hypothesize that attention mechanisms inherently encode context utilization signals, supported by probing analysis. Based on these insights, we propose Dynamic Attention-Guided Context Decoding (DAGCD), a lightweight framework that leverages attention distributions and uncertainty signals in a single-pass decoding. Experiments on open-book QA datasets demonstrate DAGCD’s effectiveness, yielding significant improvements in faithfulness and robustness while preserving computational efficiency.

BibTeX
@inproceedings{huangyw-etal-2025-dynamic,
    title = "Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models",
    author = "Huang, Yanwen  and
      Zhang, Yong  and
      Cheng, Ning  and
      Li, Zhitao  and
      Wang, Shaojun  and
      Xiao, Jing",
    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://aclanthology.org/2025.findings-acl.269/",
    doi = "10.18653/v1/2025.findings-acl.269",
    pages = "5174--5193",
    ISBN = "979-8-89176-256-5"
}
Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models · ACL 2025