Towards Modern Topic Models: A Survey of Taxonomies and Paradigm Shifts from Algorithm‑Centric to LLM‑Centered Topic Analysis

ACL ARR 2026 January Submission1397 Authors

Keywords: topic modeling, knowledge tracing/discovering/inducing, text-to-text generation, applications

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 the transformative impact of LLM-Centric TM, characterized by several key developments: broadened and more inclusive task scope across multiple dimensions, a conceptual move away from conventional distributions toward entropy-focused metrics for evaluating topic prominence and keyword focus. We also propose a future roadmap for more optimized LLM-Centric TMs and identify critical ongoing challenges. We aim for this survey to spur closer integration between TM and LLMs and to further drive the progress of modern TM.

Paper Type: Long

Research Area: Interpretability and Analysis of Models for NLP

Research Area Keywords: topic modeling, knowledge tracing/discovering/inducing, text-to-text generation, applications

Contribution Types: Position papers, Surveys, Theory

Languages Studied: English

Submission Number: 1397