@inproceedings{zeng-etal-2026-hyperedit,
    title = "{H}yper{E}dit: Unlocking Instruction-based Text Editing in {LLM}s via Hypernetworks",
    author = "Zeng, Yiming  and
      Cao, Jinghan  and
      Li, Zexin  and
      Yu, Wanhao  and
      Ye, Zhankai  and
      Xiang, Dawei  and
      Hua, Ting  and
      Liu, Xin  and
      Gao, Shangqian  and
      Yu, Tingting",
    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.22/",
    pages = "466--480",
    ISBN = "979-8-89176-395-1",
    abstract = "Large Language Models (LLMs) have fundamentally transformed natural language processing (NLP), demonstrating remarkable capabilities across a wide spectrum of tasks. However, when applied to instruction-based text editing, LLMs continue to exhibit some limitations. Different from free-form generation, instruction-based editing requires precise, targeted modifications that respect two essential properties: faithfully implementing the specific instruction and local fidelity. Existing approaches often overlook these properties, treating editing as a generic text generation problem. As a result, they either over-edit or fail to apply modifications consistently. To address this gap, we propose HyperEdit, a framework that adaptively processes each editing request to best align with it. To achieve this, HyperEdit generates request-specific dynamic weights that guide the editing process. The computational overhead of producing these weights is minimized through a carefully designed hypernetwork. With this design, HyperEdit achieves a relatively 9{\%} improvement over the state-of-the-art editing model."
}