Elamur Research⌕
☰
home / papers / 2026 / Towards Modern Topic Models: A Survey of Taxonomies and Paradigm Shifts from Algorithm-Centric to LLM-Centered Topic Analysis

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

Paper · 2026 · Xuan Xu, Zhongliang Yang, Haolun Li et al.

Summary

Topic modeling has long depended on lightweight algorithms such as LDA and neural variational models, but large language models are changing how corpora get analysed. Earlier surveys mostly overlook this change. The authors therefore review recent work and group topic modeling methods by how deeply LLMs are involved:

  • Classical Algorithm-Centric: traditional pipelines with no LLM.
  • LLM-Assisted: an LLM improves a single stage of a conventional pipeline.
  • LLM-Centric: the LLM itself drives the analysis through prompting or agentic workflows.

For the classical group, they update existing taxonomies with work from roughly the last three years. For the two LLM groups, they introduce new taxonomies built around the roles LLMs play and how end-to-end workflows are designed. They argue that LLM-centric approaches widen the scope of the task and shift progress from tuning individual models toward engineering whole systems. The survey closes with three parts:

  • a qualitative comparison of paradigms to guide method selection;
  • a roadmap toward interactive, adaptive topic analysis systems;
  • a list of open problems.

It is a practical map for deciding between classical and LLM-based topic analysis.

Key points

  • The classical branch covers three families:

    • LDA variants such as LDA* and hLDA;
    • embedding-based models such as ETM, BERTopic, FASTopic and C-Top2Vec;
    • VAE-based NTMs (ProdLDA and successors), refined through priors, contrastive learning and optimal transport (e.g. NeuroMax, TraCo, EnCOT).

  • LLM-Assisted methods are organised by where the LLM contributes:

    • data preprocessing (AugmentTopic, LimTopic);
    • LLM-derived embeddings (DeTiME, FinBERT2);
    • post-hoc refinement (LLM-ITL);
    • evaluation (WALM, ProxAnn).

  • LLM-Centric methods fall into three groups:

    • Prompt-based TM, either one-round (e.g. LAMT) or two-round (TopicGPT, TopicGen, CHIME);
    • Agentic TM (LLooM, SPARK, Aella Explorer);
    • work that interprets LLMs themselves as topic models.

  • Table 3 compares the three paradigms on topic quality, I/O flexibility, cost and latency, scalability, privacy and multilingual transfer:

    • Traditional TM is cheap and easy to run on-prem.
    • LLM-centric TM gives the strongest quality and cross-lingual transfer, but costs more and is weaker on privacy by default.

  • The authors name three main open challenges:

    • quadratic attention cost over very long multi-document inputs;
    • the lack of a standard benchmark for this paradigm;
    • hallucinated topics and poor reproducibility.

    A resource list is published at github.com/Harrisonls2004/Towards-Modern-Topic-Models.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Beijing University of Posts and TelecommunicationsBeijing · China57 works · 32,843 citations🎓University of Science and Technology BeijingBeijing · China8 works · 315 citations

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksSocial Sciences · 1,772 worksGeneral Social Sciences · 227 works

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 3,320 works

💡 Concepts 1Key ideas and methods explained on our concept pages.Topic modeling · 47 works

Cite

Cite as Xuan Xu, Zhongliang Yang, Haolun Li, Rui Tian, Beilin Chu, J Song, Yu Li, Shaolin Tan and Linna Zhou. 2026. Towards Modern Topic Models: A Survey of Taxonomies and Paradigm Shifts from Algorithm-Centric to LLM-Centered Topic Analysis. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.326

@inproceedings{xu2026modern,
  title = {{Towards Modern Topic Models: A Survey of Taxonomies and Paradigm Shifts from Algorithm-Centric to LLM-Centered Topic Analysis}},
  author = {Xuan Xu, Zhongliang Yang, Haolun Li, Rui Tian, Beilin Chu, J Song, Yu Li, Shaolin Tan and Linna Zhou},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.326},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.326}
}

References

76 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Aly Abdelrazek, Yomna Eid, Eman Gawish, Walaa Medhat, and Ahmed Hassan. 2023. Topic modeling algorithms and applications: A survey. Information Systems, 112:102131. find
  2. Suman Adhya and Debarshi Kumar Sanyal. 2025. S2WTM: Spherical sliced-Wasserstein autoencoder for topic modeling. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 23211– 23225, Vienna, Austria. Association for Computational Ling… find
  3. Pritom Saha Akash and Kevin Chen-Chuan Chang. 2024. Enhancing Short-Text Topic Modeling with LLM-Driven Context Expansion and Prefix-Tuned VAEs. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 15635– 15646, Miami, Florida, USA. Association for Computational Linguistic… find
  4. Dimo Angelov. 2020. Top2vec: Distributed representations of topics. arXiv preprint arXiv:2008.09470.
  5. Dimo Angelov and Diana Inkpen. 2024. Topic modeling: Contextual token embeddings are all you need. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 13528–13539, Miami, Florida, USA. Association for Computational Linguistics. find
  6. Ibrahim Al Azher, Venkata Devesh Reddy Seethi, Akhil Pandey Akella, and Hamed Alhoori. 2025. LimTopic: LLM-based Topic Modeling and Text Summarization for Analyzing Scientific Articles limitations. In Proceedings of the 24th ACM/IEEE Joint Conference on Digital Libraries, JCDL ’24, pages 1– 12, New… find
  7. David M Blei, Andrew Y Ng, and Michael I Jordan. 2003. Latent dirichlet allocation. Journal of machine Learning research, 3(Jan):993–1022.
  8. HeGang Chen, Pengbo Mao, Yuyin Lu, and Yanghui Rao. 2023. Nonlinear structural equation model guided Gaussian mixture hierarchical topic modeling. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10377–10390, Toronto, Canada. A… find
  9. Jianfei Chen, Jun Zhu, Jie Lu, and Shixia Liu. 2018. Scalable training of hierarchical topic models. Proc. VLDB Endow., 11(7):826–839. find
  10. Weisi Chen, Walayat Hussain, and Junjie Chen. 2025. Glmtopic: A hybrid chinese topic model leveraging large language models. Computers, Materials & Continua, 85(1):1559–1583. find
  11. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies,…
  12. Adji B Dieng, Francisco JR Ruiz, and David M Blei. 2020. Topic modeling in embedding spaces. Transactions of the Association for Computational Linguistics, 8:439–453.
  13. Tomoki Doi, Masaru Isonuma, and Hitomi Yanaka. 2024. Topic Modeling for Short Texts with Large Language Models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop), pages 21–33, Bangkok, Thailand. Association for Computatio… find
  14. FulPhil. 2024. Agentopic: Topic modeling with llm-based agent. https://github.com/pariskang/ AgenTopic. ↗
  15. Xin Gao, Yang Lin, Ruiqing Li, Yasha Wang, Xu Chu, Xinyu Ma, and Hailong Yu. 2024. Enhancing topic interpretability for neural topic modeling through topic-wise contrastive learning. In 2024 IEEE 40th International Conference on Data Engineering (ICDE), pages 584–597. find
  16. Thomas L Griffiths and Mark Steyvers. 2004. Finding scientific topics. Proceedings of the National academy of Sciences, 101(suppl_1):5228–5235. find
  17. Maarten Grootendorst. 2022. BERTopic: Neural topic modeling with a class-based TF-IDF procedure. Preprint, arXiv:2203.05794.
  18. Mustapha Hankar, Mohammed Kasri, and Abderrahim Beni-Hssane. 2025. A comprehensive overview of topic modeling: Techniques, applications and challenges. Neurocomputing, 628:129638. find
  19. Alexander Miserlis Hoyle, Lorena Calvo-Bartolomé, Jordan Lee Boyd-Graber, and Philip Resnik. 2025. ProxAnn: Use-Oriented Evaluations of Topic Models and Document Clustering. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1587… find
  20. Chao-Chun Hsu, Erin Bransom, Jenna Sparks, Bailey Kuehl, Chenhao Tan, David Wadden, Lucy Wang, and Aakanksha Naik. 2024. CHIME: LLM-Assisted Hierarchical Organization of Scientific Studies for Literature Review Support. In Findings of the Association for Computational Linguistics: ACL 2024, pages 11… find
  21. Nakano Kappei. 2024. A Novel Approach to Topic Modeling Using Large Language Models (LLMs). find
  22. Sean Kuzco and Sam Hogan. 2025. Aella science dataset explorer. LAION research paper dataset visual explorer. MIT License. Stars: 696, Forks: 111 (accessed 2025-12-31). find
  23. Michelle S. Lam, Janice Teoh, James A. Landay, Jeffrey Heer, and Michael S. Bernstein. 2024. Concept induction: Analyzing unstructured text with high-level concepts using lloom. In Proceedings of the CHI Conference on Human Factors in Computing Systems, CHI ’24, page 1–28. ACM. find
  24. Raymond Li, Felipe Gonzalez-Pizarro, Linzi Xing, Gabriel Murray, and Giuseppe Carenini. 2023. Diversity-aware coherence loss for improving neural topic models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 1710–1722, Toront… find
  25. Zongxia Li, Lorena Calvo-Bartolomé, Alexander Miserlis Hoyle, Paiheng Xu, Daniel Kofi Stephens, Juan Francisco Fung, Alden Dima, and Jordan Lee Boyd-Graber. 2025. Large Language Models Struggle to Describe the Haystack without Human Help: A Social Science-Inspired Evaluation of Topic Models. In Proc… find
  26. Xun Liang, Jiawei Yang, Yezhaohui Wang, Chen Tang, Zifan Zheng, Shichao Song, Zehao Lin, Yebin Yang, Simin Niu, Hanyu Wang, Bo Tang, Feiyu Xiong, Keming Mao, and Zhiyu li. 2025. Surveyx: Academic survey automation via large language models. Preprint, arXiv:2502.14776. — [arXiv:2502.14776](https://arxiv.org/abs/2502.14776) find
  27. Jia Peng Lim and Hady Lauw. 2023. Disentangling transformer language models as superposed topic models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 8646–8666, Singapore. Association for Computational Linguistics. find
  28. Jia Peng Lim and Hady Lauw. 2025. Interpreting topic models in byte-pair encoding space. In Proceedings of the 31st International Conference on Computational Linguistics, pages 10810–10838, Abu Dhabi, UAE. Association for Computational Linguistics. text topic modeling via nearest neighbor augmentati… find
  29. Jianghan Liu, Ziyu Shang, Wenjun Ke, Peng Wang, Zhizhao Luo, Jiajun Liu, Guozheng Li, and Yining Li. 2025a. LLM-Guided Semantic-Aware Clustering for Topic Modeling. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 18420– 18435,… find
  30. Jiyuan Liu, Jiaxing Yan, Chunjiang Zhu, Xingyu Liu, Li Qing, and Yanghui Rao. 2025b. Neural topic modeling via contextual and graph information fusion. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 13247–13263, Suzhou, China. Association for Computa… find
  31. Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781.
  32. Nozomu Miyamoto, Masaru Isonuma, Sho Takase, Junichiro Mori, and Ichiro Sakata. 2023. Dynamic structured neural topic model with self-attention mechanism. In Findings of the Association for Computational Linguistics: ACL 2023, pages 5916–5930, Toronto, Canada. Association for Computational Linguisti… find
  33. Yida Mu, Chun Dong, Kalina Bontcheva, and Xingyi Song. 2024. Large Language Models Offer an Alternative to the Traditional Approach of Topic Modelling. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages… find
  34. Thong Nguyen, Xiaobao Wu, Xinshuai Dong, Cong-Duy T Nguyen, See-Kiong Ng, and Anh Tuan Luu. 2025. Topic modeling as multi-objective contrastive optimization. Preprint, arXiv:2402.07577. — [arXiv:2402.07577](https://arxiv.org/abs/2402.07577) find
  35. Jeffrey Pennington, Richard Socher, and Christopher D Manning. 2014. Glove: Global vectors for word representation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pages 1532–1543.
  36. Ning Lin, Haolun Li, Mingshu Liu, Chengyun Ruan, Kaibo Huang, Yukun Wei, Zhongliang Yang, and Linna Zhou. 2026. Evocorps: An evolutionary multi-agent framework for depolarizing online discourse. arXiv preprint arXiv:2602.08529. — [arXiv:2602.08529](https://arxiv.org/abs/2602.08529) find
  37. Chau Minh Pham, Alexander Hoyle, Simeng Sun, Philip Resnik, and Mohit Iyyer. 2024a. TopicGPT: A Prompt-based Topic Modeling Framework. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Pap…
  38. Yang Lin, Xinyu Ma, Xin Gao, Ruiqing Li, Yasha Wang, and Xu Chu. 2024. Combating label sparsity in short Duy-Tung Pham, Thien Trang Nguyen Vu, Tung Nguyen, Linh Van Ngo, Duc Anh Nguyen, and Thien Huu Nguyen. 2024b. NeuroMax: Enhancing neural topic modeling via maximizing mutual information and group… find
  39. Hamed Rahimi, Hubert Naacke, Camelia Constantin, and Bernd Amann. 2024. Antm: aligned neural topic models for exploring evolving topics. In Transactions on Large-Scale Data-and Knowledge-Centered Systems LVI: Special Issue on Data Management-Principles, Technologies, and Applications, pages 76–97. S… find
  40. Nishavi Ranaweera, Jiarui Xu, Suranga Seneviratne, and Aruna Seneviratne. 2025. Bertdetect: A neural topic modelling approach for android malware detection. In Companion Proceedings of the ACM on Web Conference 2025, WWW ’25, page 1802–1810, New York, NY, USA. Association for Computing Machinery. find
  41. Junaid Rashid, Jungeun Kim, and Usman Naseem. 2023a. Coherent topic modeling for creative multimodal data on social media. In Proceedings of the ACM Web Conference 2023, WWW ’23, page 3923–3927, New York, NY, USA. Association for Computing Machinery. find
  42. Junaid Rashid, Jungeun Kim, and Usman Naseem. 2023b. Incorporating Embedding to Topic Modeling for More Effective Short Text Analysis. In Companion Proceedings of the ACM Web Conference 2023, pages 73–76, Austin TX USA. ACM. find
  43. Abilasha S, Rafika Boutalbi, and Stéphane Delliaux. 2025. Multi-view topic modeling using multi-text representations. In Companion Proceedings of the ACM on Web Conference 2025, WWW ’25, page 1278–1282, New York, NY, USA. Association for Computing Machinery. find
  44. Wei Shao, Mingyang Liu, and Linqi Song. 2025. Diffetm: Diffusion process enhanced embedded topic model. Preprint, arXiv:2501.00862. — [arXiv:2501.00862](https://arxiv.org/abs/2501.00862) find
  45. Suzanna Sia, Ayush Dalmia, and Sabrina J. Mielke. 2020. Tired of topic models? clusters of pretrained word embeddings make for fast and good topics too! In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1728–1736, Online. Association for Computa… find
  46. Akash Srivastava and Charles Sutton. 2017. Autoencoding variational inference for topic models. arXiv preprint arXiv:1703.01488. — [arXiv:1703.01488](https://arxiv.org/abs/1703.01488) find
  47. Dominik Stammbach, Vilém Zouhar, Alexander Hoyle, Mrinmaya Sachan, and Elliott Ash. 2023. Revisiting Automated Topic Model Evaluation with Large Language Models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 9348–9357, Singapore. Association for Com… find
  48. Tu Vu, Manh Do, Tung Nguyen, Linh Ngo Van, Sang Dinh, and Thien Huu Nguyen. 2025. Topic modeling for short texts via optimal transport-based clustering. In Findings of the Association for Computational Linguistics: ACL 2025, pages 7666–7680, Vienna, Austria. Association for Computational Linguistics… find
  49. Hoang Tran Vuong, Tue Le, Tu Vu, Tung Nguyen, Linh Ngo Van, Sang Dinh, and Thien Huu Nguyen. 2025. HiCOT: Improving neural topic models via optimal transport and contrastive learning. In Findings of the Association for Computational Linguistics: ACL 2025, pages 13894–13920, Vienna, Austria. Associat… find
  50. Boyu Wang, Linhai Zhang, Deyu Zhou, Yi Cao, and Jiandong Ding. 2023. Neural topic modeling based on cycle adversarial training and contrastive learning. In Findings of the Association for Computational Linguistics: ACL 2023, pages 9720–9731, Toronto, Canada. Association for Computational Linguistics… find
  51. Dongsheng Wang, Dandan Guo, He Zhao, Huangjie Zheng, Korawat Tanwisuth, Bo Chen, and Mingyuan Zhou. 2022. Representing mixtures of word embeddings with mixtures of topic embeddings. Preprint, arXiv:2203.01570. — [arXiv:2203.01570](https://arxiv.org/abs/2203.01570) find
  52. Rui Wang, Ziang Li, Yi Zheng, Gongzhi Luo, Yongquan Zhou, and Yuxiang Zhou. 2025a. Topic modeling and alignment with large language models for multi-labeled text corpora. Expert Systems with Applications, 264:125737. find
  53. Rui Wang, Xing Liu, Yanan Wang, Shuyu Chang, Yuanzhi Yao, and Haiping Huang. 2025b. Mining Topics towards ChatGPT Using a Disentangled Contextualized-neural Topic Model. In Proceedings of the Eighteenth ACM International Conference on Web Search and Data Mining, pages 539–548, Hannover Germany. ACM. find
  54. Rui Wang, Jiahao Lu, Xincheng Lv, Shuyu Chang, Yansheng Wu, Yuanzhi Yao, Haiping Huang, and Guozi Sun. 2025c. Mining user preferences from online reviews with the genre-aware personalized neural topic model. In Proceedings of the ACM on Web Conference 2025, WWW ’25, page 1877–1888, New York, NY, USA… find
  55. Rui Wang, Yanan Wang, Ziang Li, Haitao Cheng, and Guozi Sun. 2025d. Distributed keyword-guided topic model with lexical knowledge supervision. ACM Trans. Knowl. Discov. Data, 19(6). find
  56. Rui Wang, Deyu Zhou, Haiping Huang, and Yongquan Zhou. 2025e. Mit: Mutual information topic model for diverse topic extraction. IEEE Transactions on Neural Networks and Learning Systems, 36(2):2523– 2537. find
  57. Lilian Weng. 2023. Llm-powered autonomous agents. lilianweng.github.io. find
  58. Xiaobao Wu, Thong Nguyen, and Anh Tuan Luu. 2024a. A survey on neural topic models: Methods, applications, and challenges. Artificial Intelligence Review, 57(2):18. find
  59. Xiaobao Wu, Thong Nguyen, Delvin Zhang, William Yang Wang, and Anh Tuan Luu. 2024b. Fastopic: Pretrained transformer is a fast, adaptive, stable, and transferable topic model. Advances in Neural Information Processing Systems, 37:84447– 84481. find
  60. Xiaobao Wu, Fengjun Pan, and Anh Tuan Luu. 2024c. Towards the TopMost: A Topic Modeling System Toolkit. Preprint, arXiv:2309.06908. find
  61. Xiaobao Wu, Fengjun Pan, Thong Nguyen, Yichao Feng, Chaoqun Liu, Cong-Duy Nguyen, and Anh Tuan Luu. 2024d. On the affinity, rationality, and diversity of hierarchical topic modeling. Preprint, arXiv:2401.14113. — [arXiv:2401.14113](https://arxiv.org/abs/2401.14113) find
  62. Weijie Xu, Wenxiang Hu, Fanyou Wu, and Srinivasan Sengamedu. 2023a. DeTiME: Diffusion-Enhanced Topic Modeling using Encoder-decoder based LLM. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 9040–9057, Singapore. Association for Computational Linguistics. find
  63. Weijie Xu, Xiaoyu Jiang, Srinivasan Sengamedu Hanumantha Rao, Francis Iannacci, and Jinjin Zhao. 2023b. vontss: vmf based semi-supervised neural topic modeling with optimal transport. In Findings of the Association for Computational Linguistics: ACL 2023, page 4433–4457. Association for Computationa… find
  64. Xuan Xu, Fufang Wen, Beilin Chu, Zhibing Fu, Qinhong Lin, Jiaqi Liu, Binjie Fei, Yu Li, Linna Zhou, and Zhongliang Yang. 2025. Finbert2: A specialized bidirectional encoder for bridging the gap in finance-specific deployment of large language models. In Proceedings of the 31st ACM SIGKDD Conference… find
  65. Xuan Xu, Zhongliang Yang, Haolun Li, Beilin Chu, Rui Tian, Yu Li, Shaolin Tan, and Linna Zhou. 2026. Llm as attention-informed ntm and topic modeling as long-input generation: Interpretability and long-context capability. Preprint, arXiv:2510.03174. — [arXiv:2510.03174](https://arxiv.org/abs/2510.03174) find
  66. Yishi Xu, Jianqiao Sun, Yudi Su, Xinyang Liu, Zhibin Duan, Bo Chen, and Mingyuan Zhou. 2023c. Context-guided embedding adaptation for effective topic modeling in low-resource regimes. Advances in Neural Information Processing Systems, 36:79959– 79979. find
  67. Yishi Xu, Dongsheng Wang, Bo Chen, Ruiying Lu, Zhibin Duan, and Mingyuan Zhou. 2022. Hyperminer: Topic taxonomy mining with hyperbolic embedding. Preprint, arXiv:2210.10625. — [arXiv:2210.10625](https://arxiv.org/abs/2210.10625) find
  68. Xiaohao Yang, He Zhao, Dinh Phung, Wray Buntine, and Lan Du. 2025a. LLM Reading Tea Leaves: Automatically Evaluating Topic Models with Large Language Models. Transactions of the Association for Computational Linguistics, 13:357–375. find
  69. Xiaohao Yang, He Zhao, Weijie Xu, Yuanyuan Qi, Jueqing Lu, Dinh Phung, and Lan Du. 2025b. Neural Topic Modeling with Large Language Models in the Loop. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1377–1401, Vienna, Austria… find
  70. Lele Yut, Ce Zhang, Yingxia Shao, and Bin Cui. 2017. Lda*: a robust and large-scale topic modeling system. Proc. VLDB Endow., 10(11):1406–1417. find
  71. Bowen Zhang, Yi Yang, Fuqiang Niu, Xianghua Fu, Genan Dai, and Hu Huang. 2025. SPARK: Simulating the co-evolution of stance and topic dynamics in online discourse with LLM-based agents. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 23061–23073, Suzh… find
  72. Delvin Ce Zhang and Hady W. Lauw. 2024. Topic modeling on document networks with dirichlet optimal transport barycenter. IEEE Transactions on Knowledge and Data Engineering, 36(3):1328–1340. find
  73. Linhai Zhang, Xuemeng Hu, Boyu Wang, Deyu Zhou, Qian-Wen Zhang, and Yunbo Cao. 2022. Pre-training and fine-tuning neural topic model: A simple yet effective approach to incorporating external knowledge. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volum… find
  74. Yongmao Zhang, Kai Qiao, Zhengyan Wang, Ningning Liang, Dekui Ma, Wenyao Sun, Jian Chen, and Bin Yan. 2026. POSIM: A multi-agent simulation framework for social media public opinion evolution and governance. arXiv preprint arXiv:2603.23884. — [arXiv:2603.23884](https://arxiv.org/abs/2603.23884) find
  75. He Zhao, Dinh Phung, Viet Huynh, Trung Le, and Wray Buntine. 2020. Neural topic model via optimal transport. arXiv preprint arXiv:2008.13537. — [arXiv:2008.13537](https://arxiv.org/abs/2008.13537) find
  76. Tuğba Çelikten and Aytuğ Onan. 2025. Topic modeling through rank-based aggregation and llms: An approach for ai and human-generated scientific texts. Knowledge-Based Systems, 314:113219. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/xu-2026-modern-topic-models-survey-taxonomies/