@inproceedings{zhao-etal-2025-sparse,
    title = "Sparse Activation Editing for Reliable Instruction Following in Narratives",
    author = "Zhao, Runcong  and
      Cao, Chengyu  and
      Zhu, Qinglin  and
      Ly, Xiucheng  and
      Shao, Shun  and
      Gui, Lin  and
      Xu, Ruifeng  and
      He, Yulan",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1311/",
    pages = "25828--25843",
    ISBN = "979-8-89176-332-6",
    abstract = "Complex narrative contexts often challenge language models' ability to follow instructions, and existing benchmarks fail to capture these difficulties. To address this, we propose Concise-SAE, a training-free framework that improves instruction following by identifying and editing instruction-relevant neurons using only natural language instructions, without requiring labelled data. To thoroughly evaluate our method, we introduce FreeInstruct, a diverse and realistic benchmark that highlights the challenges of instruction following in narrative-rich settings. While initially motivated by complex narratives, Concise-SAE demonstrates state-of-the-art instruction adherence across varied tasks without compromising generation quality."
}