ACL Findings2026
Towards Modern Topic Models: A Survey of Taxonomies and Paradigm Shifts from Algorithm-Centric to LLM-Centered Topic Analysis
Xuan Xu, Zhongliang Yang, Haolun Li, Rui Tian, Beilin Chu, Jia Song, Yu Li, Shaolin Tan, Linna Zhou
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 LLMdriven 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 systemlevel 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. 1
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Representing Mixtures of Word Embeddings with Mixtures of Topic Embeddings cites Neural Topic Model via Optimal Transport
- HyperMiner: Topic Taxonomy Mining with Hyperbolic Embedding cites Representing Mixtures of Word Embeddings with Mixtures of Topic Embeddings
- FASTopic: Pretrained Transformer is a Fast, Adaptive, Stable, and Transferable Topic Model cites Representing Mixtures of Word Embeddings with Mixtures of Topic Embeddings
- FASTopic: Pretrained Transformer is a Fast, Adaptive, Stable, and Transferable Topic Model cites HyperMiner: Topic Taxonomy Mining with Hyperbolic Embedding
- FASTopic: Pretrained Transformer is a Fast, Adaptive, Stable, and Transferable Topic Model cites Neural Topic Model via Optimal Transport
Builds on31
- Neural Topic Model via Optimal TransportHe Zhao, Dinh Phung, Viet Huynh, Trung Le et al.ICLR 2021 · 100 citations
- FASTopic: Pretrained Transformer is a Fast, Adaptive, Stable, and Transferable Topic ModelXiaobao Wu, Thong Nguyen, Delvin Zhang, William Yang Wang et al.NeurIPS 2024 · 67 citations
- Representing Mixtures of Word Embeddings with Mixtures of Topic EmbeddingsDongsheng Wang, Dandan Guo, He Zhao, Huangjie Zheng et al.ICLR 2022 · 56 citations
- Concept Induction: Analyzing Unstructured Text with High-Level Concepts Using LLooMMichelle S. Lam, Janice Teoh, James A. Landay, Jeffrey Heer et al.CHI 2024 · 46 citations
- HyperMiner: Topic Taxonomy Mining with Hyperbolic EmbeddingYishi Xu, Dongsheng Wang, Bo Chen, Ruiying Lu et al.NeurIPS 2022 · 38 citations
Related papers
- A Survey of Large Language Models for Text-Guided Molecular Discovery: From Molecule Generation to OptimizationZiqing Wang, Kexin Zhang, Zihan Zhao, Yibo Wen et al.ACL 2026 · 10 citations
- Data Augmentation using LLMs: Data Perspectives, Learning Paradigms and ChallengesBosheng Ding, Chengwei Qin, Ruochen Zhao, Tianze Luo et al.ACL Findings 2024 · 106 citations
- From Automation to Autonomy: A Survey on Large Language Models in Scientific DiscoveryTianshi Zheng, Zheye Deng, Hong Ting Tsang, Weiqi Wang et al.EMNLP 2025 · 5 citations
- From Selection to Generation: A Survey of LLM-based Active LearningYu Xia, Subhojyoti Mukherjee, Zhouhang Xie, Junda Wu et al.ACL 2025 · 18 citations
- From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judgeDawei Li, Bohan Jiang, Liangjie Huang, Alimohammad Beigi et al.EMNLP 2025 · 37 citations
