@inproceedings{kim-etal-2026-persona,
    title = "Persona Switch: Mixing Distinct Perspectives in Decoding Time",
    author = "Kim, Junseok  and
      Yang, Nakyeong  and
      Jung, Kyomin",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.findings-eacl.101/",
    pages = "1955--1967",
    ISBN = "979-8-89176-386-9",
    abstract = "Role-play prompting is known to steer the behavior of language models by injecting a persona into the prompt, improving their zero-shot reasoning capabilities. However, such improvements are inconsistent across different tasks or instances. This inconsistency suggests that zero-shot and role-play prompting may offer complementary strengths rather than one being universally superior. Building on this insight, we propose **Persona Switch**, a novel decoding method that dynamically combines the benefits of both prompting strategies. Our method proceeds step-by-step, selecting the better output between zero-shot and role-play prompting at each step by comparing their output confidence, as measured by the logit gap. Experiments with widely-used LLMs demonstrate that Persona Switch consistently outperforms competitive baselines, achieving up to 5.13{\%} accuracy improvement. Furthermore, we show that output confidence serves as an informative measure for selecting the more reliable output."
}