@inproceedings{zhao-etal-2025-neuron,
    title = "Neuron Empirical Gradient: Discovering and Quantifying Neurons' Global Linear Controllability",
    author = "Zhao, Xin  and
      Jiang, Zehui  and
      Yoshinaga, Naoki",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.1041/",
    pages = "21446--21477",
    ISBN = "979-8-89176-251-0",
    abstract = "While feed-forward neurons in pre-trained language models (PLMs) can encode knowledge, past research targeted a small subset of neurons that heavily influence outputs.This leaves the broader role of neuron activations unclear, limiting progress in areas like knowledge editing.We uncover a global linear relationship between neuron activations and outputs using neuron interventions on a knowledge probing dataset.The gradient of this linear relationship, which we call the **neuron empirical gradient (NEG)**, captures how changes in activations affect predictions.To compute NEG efficiently, we propose **NeurGrad**, enabling large-scale analysis of neuron behavior in PLMs.We also show that NEG effectively captures language skills across diverse prompts through skill neuron probing. Experiments on **MCEval8k**, a multi-genre multiple-choice knowledge benchmark, support NEG{'}s ability to represent model knowledge. Further analysis highlights the key properties of NEG-based skill representation: efficiency, robustness, flexibility, and interdependency.Code and data are released."
}