LLM-Guided Lifecycle-Aware Clustering of Multi-Turn Customer Support Conversations
Not on the map. Why?
Abstract (arXiv)
Clustering customer chat data is vital for cloud providers handling multi service queries. Traditional methods struggle with overlapping concerns and create broad, static clusters that degrade over time. Reclustering disrupts continuity, making issue tracking difficult. We propose an adaptive system that segments multi turn chats into service specific concerns and incrementally refines clusters as new issues arise. Cluster quality is tracked via DaviesBouldin Index and Silhouette Scores, with LLM based splitting applied only to degraded clusters. Our method improves Silhouette Scores by over 100% and reduces DBI by 65.6% compared to baselines, enabling scalable, real time analytics without full reclustering.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 16 of its 40 references that are in the map. First posted on arXiv 7 Jan 2026.
Builds on
16 of 40 references.
References · 16
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
- 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
- 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
- 2021Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Modelscited by 462
- 2020Supervised Contrastive Learning for Pre-trained Language Model Fine-tuningcited by 275
- 2024Survey of Large Multimodal Model Datasets, Application Categories and Taxonomycited by 17
- 2025SweEval: Do LLMs Really Swear? A Safety Benchmark for Testing Limits for Enterprise Usecited by 15
- 2025Hard Negative Mining for Domain-Specific Retrieval in Enterprise Systemscited by 14
- 2024LLM for Barcodes: Generating Diverse Synthetic Data for Identity Documentscited by 12
- 2024Enhancing Document AI Data Generation Through Graph-Based Synthetic Layoutscited by 12
- 2025Tokenization Matters: Improving Zero-Shot NER for Indic Languagescited by 12
4 more
- 2025Clinical QA 2.0: Multi-Task Learning for Answer Extraction and Categorizationcited by 8
- 2025Hybrid AI for Responsive Multi-Turn Online Conversations with Novel Dynamic Routing and Feedback Adaptationcited by 6
- 2023Multi-turn Dialogue Comprehension from a Topic-aware Perspectivecited by 4
- 2025Review of Tools for Zero-Code LLM Based Application Developmentcited by 4
Built on by
Citing papers per year: 2026: 2.
2 papers.