@inproceedings{lee-etal-2025-spectrum,
    title = "{SP}e{C}trum: A Grounded Framework for Multidimensional Identity Representation in {LLM}-Based Agent",
    author = "Lee, Keyeun  and
      Kim, Seo Hyeong  and
      Lee, Seolhee  and
      Eun, Jinsu  and
      Ko, Yena  and
      Jeon, Hayeon  and
      Kim, Esther Hehsun  and
      Cho, Seonghye  and
      Yang, Soeun  and
      Kim, Eun-mee  and
      Lim, Hajin",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.naacl-long.356/",
    pages = "6971--6991",
    ISBN = "979-8-89176-189-6",
    abstract = "Existing methods for simulating individual identities often oversimplify human complexity, which may lead to incomplete or flattened representations. To address this, we introduce SPeCtrum, a grounded framework for constructing authentic LLM agent personas by incorporating an individual{'}s multidimensional self-concept. SPeCtrum integrates three core components: Social Identity (S), Personal Identity (P), and Personal Life Context (C), each contributing distinct yet interconnected aspects of identity. To evaluate SPeCtrum{'}s effectiveness in identity representation, we conducted automated and human evaluations. Automated evaluations using popular drama characters showed that Personal Life Context (C){---}derived from short essays on preferences and daily routines{---}modeled characters' identities more effectively than Social Identity (S) and Personal Identity (P) alone and performed comparably to the full SPC combination. In contrast, human evaluations involving real-world individuals found that the full SPC combination provided a more comprehensive self-concept representation than C alone. Our findings suggest that while C alone may suffice for basic identity simulation, integrating S, P, and C enhances the authenticity and accuracy of real-world identity representation. Overall, SPeCtrum offers a structured approach for simulating individuals in LLM agents, enabling more personalized human-AI interactions and improving the realism of simulation-based behavioral studies."
}