@inproceedings{zhang-etal-2026-eyemulator,
    title = "{E}ye{M}ulator: Improving Code Language Models by Mimicking Human Visual Attention",
    author = "Zhang, Yifan  and
      Huang, Chen  and
      Zhang, Yueke  and
      Zhang, Jiahao  and
      Li, Toby Jia-Jun  and
      McMillan, Collin  and
      Leach, Kevin  and
      Huang, Yu",
    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.1158/",
    pages = "25259--25272",
    ISBN = "979-8-89176-390-6",
    abstract = "Code Language Models (CodeLLMs) traditionally learn attention based solely on statistical input-output token correlations ({''}machine attention''). In contrast, human developers rely on intuition, selectively fixating on semantically salient tokens during program comprehension. We present EyeMulator, a model-agnostic technique to align CodeLLM attention with human visual attention without architectural changes. By extracting scan paths from eye-tracking data, we derive token-level attention weights used to augment the loss function during fine-tuning. This induces the model to mimic human focus. Our evaluation across StarCoder, Llama-3.2, and DeepSeek-Coder shows that EyeMulator significantly outperforms baselines, achieving gains of over 30 CodeBLEU points in translation and up to 22 BERTScore points in summarization. Ablation studies confirm that these gains stem directly from replicating human attention dynamics. Artifacts are available at https://zenodo.org/records/17205682."
}