Text Clustering

Follow this topic Ask about this topic

Latest papers

13 papers1 paper in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

RAILS: Retrieval-Augmented Incremental LLM Clustering at Scale
Sep 21, 2026Armin Oliya, Aleksandra Sawczuk, Radosław BiałobrzeskiClustering Unsupervised Clustering
Zendesk
Randomized SVD Approximations for Spectral Co-Clustering of Word-Document Matrices
Sep 16, 2026Fateme Mazdarani, Carlos ToxtliClustering Randomized Sketching
School of Computing Clemson University Clemson, SC, USA
When Can We Work in Embedding Space? What Text Embeddings Preserve
Aug 31, 2026Simon FreyaldenhovenText Embeddings Latent Variable Models
Federal Reserve Bank of Philadelphia
Designing AI Pipelines for Decision-Ready ITSM Intelligence
Aug 13, 2026Archan Dutta, Yash Dharmadhikari, Marat Valiullin +2AI-Assisted Decision Making Text Clustering
Automation Anywhere
A Cascaded Unsupervised-Supervised NLP Pipeline for Detecting Accusatory Language in Public Procurement
Aug 12, 2026Bryan Torres, Daniel Riofrío, José Vega-Sánchez +4Text Clustering
Colegio de Ciencias e Ingenierías “El Politécnico”, Universidad San Francisco de Quito (USFQ), Diego de Robles S/N, Quito 170157 · Faculty of Engineering and Applied Sciences, Telecommunications Engineering, ETEL Research Group, Universidad de Las Américas (UDLA), 170503 Quito, Ecuador · Departamento de Estudios Organizacionales y Desarrollo Humano, Escuela Politécnica Nacional, Quito 170525, Ecuador +1
Beyond Looking Up, Try Looking Around: Harmonizing Global Structure and Local Consistency in Optimal Transport for Short Text Clustering
Jul 12, 2026Zhihao Yao, Yuxuan Gu, Jixuan Yin +1Clustering Unsupervised Clustering
Harbin Engineering University, China · Harbin Institute of Technology, China
Agentic Clustering: Controllable Text Taxonomies via Multi-Agent Refinement
May 31, 2026Simon Löwe, Emily SilcockMulti-Agent LLM Systems Clustering
Burning Glass Institute · Harvard University
GUT-IS: A Data-Driven Approach to Integrating Constructs and Their Relations in Information Systems
May 18, 2026Maximilian Reinhardt, Jonas Scharfenberger, Burkhardt FunkLatent Variable Models Clustering
Institute of Information Systems Leuphana University Lüneburg, Germany
TextClusterLab: An Integrated Framework for Reliable Text Clustering Studies
May 17, 2026Daoming Wan, Yizheng Huang, Jimmy X. HuangClustering Synthetic Data Generation
Information Retrieval and Knowledge Management Research Lab, York University Toronto, Ontario, Canada
Leveraging Weighted Syntactic and Semantic Context Assessment Summary (wSSAS) Towards Text Categorization Using LLMs
Apr 13, 2026Shreeya Verma Kathuria, Nitin Mayande, Sharookh Daruwalla +2Text Clustering Text Classification
Tellagence Inc. · Villanova School of Business, Villanova University
From Topic to Transition Structure: Unsupervised Concept Discovery at Corpus Scale via Predictive Associative Memory
Mar 19, 2026Jason DuryUnsupervised Visual Concept Discovery Text Clustering
Independent Researcher
Incremental Graph Construction Enables Robust Spectral Clustering of Texts
Mar 3, 2026Marko Pranjić, Boshko Koloski, Nada Lavrač +2Text Clustering Clustering
Joˇzef Stefan Institute and International Postgraduate School, Ljubljana, Slovenia. · University of Ljubljana, Faculty of Computer and Information Science, Ljubljana, Slovenia.
Hybrid Topic-Semantic Labeling and Graph Embeddings for Unsupervised Legal Document Clustering
Aug 31, 2025Deepak Bastola, Woohyeok ChoiText Clustering Legal Document Analysis
Department of Mathematical Sciences, Salisbury University · Department of Mathematics and Statistics, Carleton College

Sep 21, 2026J/K move · Enter open · S save

RAILS: Retrieval-Augmented Incremental LLM Clustering at Scale

Armin Oliya, Aleksandra Sawczuk, Radosław Białobrzeski

Zendesk

Clustering Unsupervised Clustering Text Clustering Semantic Clustering

Open paper AskPDF arXiv

Using a Large Language Model (LLM) as the clusterer at production scale is hard: prompts cannot hold the entire label space, and per-document serial processing does not deliver the throughput real workloads require. We present RAILS, a retrieval-augmented incremental LLM clusterer that turns clustering into a simple loop over a growing label pool and scales through document batching with bounded concurrency. On six public benchmarks RAILS exceeds the strongest prior LLM-clustering method on average, lifting accuracy from 51.2% to 59.3%, NMI from 67.2% to 74.8%, and ARI from 45.4% to 54.7%. We further report production-deployment evidence from a SaaS ticket-topic-discovery pipeline, where RAILS has replaced a traditional HDBSCAN stage with higher clustering quality, transparent prompt-driven control, and stateful incremental operation.