@inproceedings{xie-etal-2026-beyond,
    title = "Beyond Prompt Engineering: A Systematic Analysis of Prompt Lexical Sensitivity and Its Impacts on Quality",
    author = "Xie, Qipeng  and
      Liang, Zi  and
      Wu, Jiafei  and
      Chen, Yufei  and
      Wang, Weizheng  and
      Ma, Wenao  and
      Ming, Zhong  and
      Yang, Haiqin  and
      Wu, Kaishun",
    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.2084/",
    pages = "41998--42012",
    ISBN = "979-8-89176-395-1",
    abstract = "Large Language Models (LLMs) often exhibit extreme sensitivity to surface-level prompt variations, where minor lexical perturbations trigger disproportionate performance fluctuations. Moving beyond black-box optimization or coarse-grained templates, we conduct the first analysis of n-gram token-level mechanisms, leveraging a large-scale dataset of 132,000 prompt variants. Our investigation uncovers the Scaling Law of Prompt Performance Stability: higher average performance is inherently associated with lower variance and greater stability. We identify that this robustness is driven by two linguistic pillars: Domain-Specific Terminology, which anchors semantic boundaries, and Explicit Action Directives, which formalize reasoning trajectories. By narrowing the model{'}s interpretative space, these patterns effectively ``lock'' the generation process. We operationalize these findings into an automated Prompt-Refining Agent that autonomously restructures queries via domain anchoring and operational constraints. Empirical results show a 40.7{\%} reduction in performance variance for code generation, offering a statistically grounded framework for robust prompt engineering."
}