@inproceedings{poonia-jain-2025-dissecting,
    title = "Dissecting Persona-Driven Reasoning in Language Models via Activation Patching",
    author = "Poonia, Ansh  and
      Jain, Maeghal",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.1335/",
    doi = "10.18653/v1/2025.findings-emnlp.1335",
    pages = "24553--24566",
    ISBN = "979-8-89176-335-7",
    abstract = "Large language models (LLMs) exhibit remarkable versatility in adopting diverse personas. In this study, we examine how assigning a persona influences a model{'}s reasoning on an objective task. Using activation patching, we take a first step toward understanding how key components of the model encode persona-specific information. Our findings reveal that the early Multi-Layer Perceptron (MLP) layers attend not only to the syntactic structure of the input but also process its semantic content. These layers transform persona tokens into richer representations, which are then used by the middle Multi-Head Attention (MHA) layers to shape the model{'}s output. Additionally, we identify specific attention heads that disproportionately attend to racial and color-based identities."
}