@inproceedings{xu-etal-2026-towards,
    title = "Towards Modern Topic Models: A Survey of Taxonomies and Paradigm Shifts from Algorithm-Centric to {LLM}-Centered Topic Analysis",
    author = "Xu, Xuan  and
      Yang, Zhongliang  and
      Li, Haolun  and
      Tian, Rui  and
      Chu, Beilin  and
      Song, J  and
      Li, Yu  and
      Tan, Shaolin  and
      Zhou, Linna",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.326/",
    pages = "6536--6561",
    ISBN = "979-8-89176-395-1",
    abstract = "LLMs have become foundational across many NLP applications, driving a shift from an algorithm-centric to a context-centric paradigm. As an important task in text mining, the landscape of topic modeling (TM) is similarly being reshaped by a growing body of LLM-driven research.We review recent TM developments and categorize existing methods into three groups: Classical Algorithm-Centric, LLM-Assisted, and LLM-Centric. For traditional algorithm-centric methods, we refine prior taxonomies and highlight recent advances. For the LLM-Assisted and LLM-Centric settings, we introduce a new taxonomy that emphasizes the role of LLMs and the design of end-to-end workflows, respectively. We examine two key transformations brought by LLM-centric TM: expanded task scope and a shift from model-level improvements to system-level engineering. We also propose a future roadmap for more optimized LLM-Centric TMs and identify ongoing critical challenges. We aim for this survey to spur closer integration between TM and LLMs and to further drive the progress of modern TM."
}