mlsanityData to 14 Oct 2026

RAILS: Retrieval-Augmented Incremental LLM Clustering at Scale

arXiv 2609.24464 ↗First posted 21 Sep 2026cs.LGcited by 0

On the map: Retrieval-augmented generation → Generation and context integration also fits: RAG pipeline design and evaluation

Abstract (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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 12 of its 27 references that are in the map. First posted on arXiv 21 Sep 2026.

Builds on

12 of 27 references.

References · 12

  1. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  2. 2018FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluationcited by 254
  3. 2020MTOP: A Comprehensive Multilingual Task-Oriented Semantic Parsing Benchmarkcited by 158
  4. 2021Few-NERD: A Few-Shot Named Entity Recognition Datasetcited by 152
  5. 2023ClusterLLM: Large Language Models as a Guide for Text Clusteringcited by 70
  6. 2023Goal-Driven Explainable Clustering via Language Descriptionscited by 58
  7. 2024Text Clustering as Classification with LLMscited by 16
  8. 2024Dial-In LLM: Human-Aligned LLM-in-the-loop Intent Clustering for Customer Service Dialoguescited by 11
  9. 2025LLMs Enable Bag-of-Texts Representations for Short-Text Clusteringcited by 2
  10. 2026LLM-Guided Lifecycle-Aware Clustering of Multi-Turn Customer Support Conversationscited by 2
  11. 2026Optimized Algorithms for Text Clustering with LLM-Generated Constraintscited by 2
  12. 2026PRISM: LLM-Guided Semantic Clustering for High-Precision Topicscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Efficient Clustering with Quality Guardrails for LLM-based Recommender Systems at Industry Scale
  2. 2025Cluster-based Adaptive Retrieval: Dynamic Context Selection for RAG Applications
  3. 2025ClusterFusion: Hybrid Clustering with Embedding Guidance and LLM Adaptation
  4. 2025Efficient Latent Semantic Clustering for Scaling Test-Time Computation of LLMs
  5. 2025EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corpora
  6. 2026Efficient Multivector Retrieval with Token-Aware Clustering and Hierarchical Indexing
  7. 2025CentroidKV: Efficient Long-Context LLM Inference via KV Cache Clustering
  8. 2025MODE: Mixture of Document Experts for RAG