@inproceedings{lan-etal-2025-attention,
    title = "Attention Consistency for {LLM}s Explanation",
    author = "Lan, Tian  and
      Xu, Jinyuan  and
      He, Xue  and
      Hwang, Jenq-Neng  and
      Li, Lei",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.91/",
    doi = "10.18653/v1/2025.findings-emnlp.91",
    pages = "1736--1750",
    ISBN = "979-8-89176-335-7",
    abstract = "Understanding the decision-making processes of large language models (LLMs) is essential for their trustworthy development and deployment, however, current interpretability methods often face challenges such as low resolution and high computational cost. To address these limitations, we propose the Multi-Layer Attention Consistency Score (MACS), a novel, lightweight, and easily deployable heuristic for estimating the importance of input tokens in decoder-based models. MACS measures contributions of input tokens based on the consistency of maximal attention. Empirical evaluations demonstrate that MACS achieves a favorable trade-off between interpretability quality and computational efficiency, showing faithfulness comparable to complex techniques with a 22{\%} decrease in VRAM usage and 30{\%} reduction in latency."
}