mlsanityData to 14 Oct 2026

ClusterLLM: Large Language Models as a Guide for Text Clustering

arXiv 2305.14871 ↗First posted 24 May 2023cs.CLcited by 70

Not on the map. Why?

Abstract (arXiv)

We introduce ClusterLLM, a novel text clustering framework that leverages feedback from an instruction-tuned large language model, such as ChatGPT. Compared with traditional unsupervised methods that builds upon "small" embedders, ClusterLLM exhibits two intriguing advantages: (1) it enjoys the emergent capability of LLM even if its embeddings are inaccessible; and (2) it understands the user's preference on clustering through textual instruction and/or a few annotated data. First, we prompt ChatGPT for insights on clustering perspective by constructing hard triplet questions <does A better correspond to B than C>, where A, B and C are similar data points that belong to different clusters according to small embedder. We empirically show that this strategy is both effective for fine-tuning small embedder and cost-efficient to query ChatGPT. Second, we prompt ChatGPT for helps on clustering granularity by carefully designed pairwise questions <do A and B belong to the same category>, and tune the granularity from cluster hierarchies that is the most consistent with the ChatGPT answers. Extensive experiments on 14 datasets show that ClusterLLM consistently improves clustering quality, at an average cost of ~0.6 per dataset. The code will be available at https://github.com/zhang-yu-wei/ClusterLLM.

Key facts. Cited by 70 papers in the map (data through 14 Oct 2026). Builds on 43 of its 92 references that are in the map. First posted on arXiv 24 May 2023.

Builds on

43 of 92 references.

References · 43

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  5. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  6. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  7. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  8. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,028
  9. 2023ChatGPT Outperforms Crowd-Workers for Text-Annotation Taskscited by 870
  10. 2015Unsupervised Deep Embedding for Clustering Analysiscited by 767
  11. 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 541
  12. 2020GoEmotions: A Dataset of Fine-Grained Emotionscited by 486
31 more
  1. 2021Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Modelscited by 463
  2. 2021Large Dual Encoders Are Generalizable Retrieverscited by 456
  3. 2020Efficient Intent Detection with Dual Sentence Encoderscited by 433
  4. 2019An Evaluation Dataset for Intent Classification and Out-of-Scope Predictioncited by 386
  5. 2020SCAN: Learning to Classify Images without Labelscited by 352
  6. 2022One Embedder, Any Task: Instruction-Finetuned Text Embeddingscited by 333
  7. 2016Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoderscited by 220
  8. 2022Generalized Category Discoverycited by 211
  9. 2016Joint Unsupervised Learning of Deep Representations and Image Clusterscited by 205
  10. 2023AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotatorscited by 172
  11. 2021Open-World Semi-Supervised Learningcited by 165
  12. 2020MTOP: A Comprehensive Multilingual Task-Oriented Semantic Parsing Benchmarkcited by 158
  13. 2021Few-NERD: A Few-Shot Named Entity Recognition Datasetcited by 152
  14. 2021SPICE: Semantic Pseudo-labeling for Image Clusteringcited by 104
  15. 2019FewRel 2.0: Towards More Challenging Few-Shot Relation Classificationcited by 94
  16. 2021Supporting Clustering with Contrastive Learningcited by 90
  17. 2023Can ChatGPT Reproduce Human-Generated Labels? A Study of Social Computing Taskscited by 89
  18. 2018Ultra-Fine Entity Typingcited by 87
  19. 2020Discovering New Intents with Deep Aligned Clusteringcited by 68
  20. 2021Clustering-friendly Representation Learning via Instance Discrimination and Feature Decorrelationcited by 65
  21. 2023Goal-Driven Explainable Clustering via Language Descriptionscited by 58
  22. 2019Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster Refinementcited by 56
  23. 2019Meta-Learning with Dynamic-Memory-Based Prototypical Network for Few-Shot Event Detectioncited by 54
  24. 2021TWEAC: Transformer with Extendable QA Agent Classifierscited by 37
  25. 2022Generalized Category Discovery with Decoupled Prototypical Networkcited by 35
  26. 2020GATCluster: Self-Supervised Gaussian-Attention Network for Image Clusteringcited by 32
  27. 2023Improving Contrastive Learning of Sentence Embeddings from AI Feedbackcited by 29
  28. 2022New Intent Discovery with Pre-training and Contrastive Learningcited by 28
  29. 2019A Framework for Deep Constrained Clustering -- Algorithms and Advancescited by 24
  30. 2021Deep Conditional Gaussian Mixture Model for Constrained Clusteringcited by 14
  31. 2022Open Relation and Event Type Discovery with Type Abstractioncited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 24; 2025: 27; 2026: 14.

70 papers.

Sort:

By area:

  1. 2024A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directionscited by 121
  2. 2024LLM-Rubric: A Multidimensional, Calibrated Approach to Automated Evaluation of Natural Language Textscited by 87
  3. 2025Organize the Web: Constructing Domains Enhances Pre-Training Data Curationcited by 76
  4. 2023Large Language Models Enable Few-Shot Clusteringcited by 72
  5. 2024Are Large Language Models Good Prompt Optimizers?cited by 37
  6. 2024Tool-Planner: Task Planning with Clusters across Multiple Toolscited by 33
  7. 2025AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprisecited by 33
  8. 2024CHIME: LLM-Assisted Hierarchical Organization of Scientific Studies for Literature Review Supportcited by 29
  9. 2024Answer is All You Need: Instruction-following Text Embedding via Answering the Questioncited by 27
  10. 2024Knowledge Navigator: LLM-guided Browsing Framework for Exploratory Search in Scientific Literaturecited by 17
  11. 2024Text Clustering as Classification with LLMscited by 16
  12. 2023Generalized Category Discovery with Large Language Models in the Loopcited by 15
38 more
  1. 2024OntoChat: a Framework for Conversational Ontology Engineering using Language Modelscited by 15
  2. 2024Eliciting Informative Text Evaluations with Large Language Modelscited by 15
  3. 2023DORIS-MAE: Scientific Document Retrieval using Multi-level Aspect-based Queriescited by 11
  4. 2023Bias in Emotion Recognition with ChatGPTcited by 11
  5. 2024Dial-In LLM: Human-Aligned LLM-in-the-loop Intent Clustering for Customer Service Dialoguescited by 11
  6. 2024DiscipLink: Unfolding Interdisciplinary Information Seeking Process via Human-AI Co-Explorationcited by 10
  7. 2025Context-Aware Hierarchical Taxonomy Generation for Scientific Papers via LLM-Guided Multi-Aspect Clusteringcited by 10
  8. 2024Context-Aware Clustering using Large Language Modelscited by 9
  9. 2025LLLMs: A Data-Driven Survey of Evolving Research on Limitations of Large Language Modelscited by 9
  10. 2025From Papers to Panoramas: Building Hierarchies of Scientific Literature at Scalecited by 8
  11. 2024Organizing Unstructured Image Collections using Natural Languagecited by 7
  12. 2024A Survey of Ontology Expansion for Conversational Understandingcited by 6
  13. 2025GLEAN: Active Generalized Category Discovery with Diverse LLM Feedbackcited by 6
  14. 2024Exploring Key Point Analysis with Pairwise Generation and Graph Partitioningcited by 4
  15. 2024Deep Spectral Clustering via Joint Spectral Embedding and Kmeanscited by 4
  16. 2025Summaries as Centroids for Interpretable and Scalable Text Clusteringcited by 4
  17. 2025TestNUC: Enhancing Test-Time Computing Approaches and Scaling through Neighboring Unlabeled Data Consistencycited by 4
  18. 2025Cequel: Cost-Effective Querying of Large Language Models for Text Clusteringcited by 3
  19. 2025LLM-as-a-qualitative-judge: automating error analysis in natural language generationcited by 3
  20. 2025Co-DETECT: Collaborative Discovery of Edge Cases in Text Classificationcited by 3
  21. 2025LLM-MemCluster: Empowering Large Language Models with Dynamic Memory for Text Clusteringcited by 3
  22. 2024Can Your Model Tell a Negation from an Implicature? Unravelling Challenges With Intent Encoderscited by 2
  23. 2024Clustering by Mining Density Distributions and Splitting Manifold Structurecited by 2
  24. 2024Information-Theoretic Generative Clustering of Documentscited by 2
  25. 2025SPILL: Domain-Adaptive Intent Clustering based on Selection and Pooling with Large Language Modelscited by 2
  26. 2025Bootstrap Deep Spectral Clustering with Optimal Transportcited by 2
  27. 2025LLMs Enable Bag-of-Texts Representations for Short-Text Clusteringcited by 2
  28. 2025When Facts Change: Probing LLMs on Evolving Knowledge with evolveQAcited by 2
  29. 2026Bridging the Semantic Gap for Categorical Data Clustering via Large Language Modelscited by 2
  30. 2026Optimized Algorithms for Text Clustering with LLM-Generated Constraintscited by 2
  31. 2023TopicGPT: A Prompt-based Topic Modeling Frameworkcited by 1
  32. 2024ZeroDL: Zero-shot Distribution Learning for Text Clustering via Large Language Modelscited by 1
  33. 2024Interactive Topic Models with Optimal Transportcited by 1
  34. 2025Fair Clustering via Alignmentcited by 1
  35. 2025What Lives? A meta-analysis of diverse opinions on the definition of lifecited by 1
  36. 2025ClusterFusion: Hybrid Clustering with Embedding Guidance and LLM Adaptationcited by 1
  37. 2026PRISM: LLM-Guided Semantic Clustering for High-Precision Topicscited by 1
  38. 2026ANCHOR: Abductive Network Construction with Hierarchical Orchestration for Reliable Probability Inference in Large Language Modelscited by 1

50 most cited of 70 All 70 (JSON)