LLM-Guided Lifecycle-Aware Clustering of Multi-Turn Customer Support Conversations

2026-01-07

arXiv.org

AI Summary

This work addresses the limitations of traditional clustering methods in multi-turn customer support dialogues, which often yield static, overly broad clusters that degrade over time, while full reclustering disrupts continuity in issue tracking. To overcome this, the authors propose a lifecycle-aware incremental clustering mechanism that first segments dialogues by service focus and then leverages a large language model (LLM) to dynamically split quality-degraded clusters without requiring global reclustering. The approach significantly enhances clustering quality, achieving over a 100% improvement in silhouette coefficient and a 65.6% reduction in Davies–Bouldin index. It effectively balances timeliness, coherence, and scalability, enabling real-time analysis of customer conversations.

Technology Category

• Machine Learning: Clustering
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Conversational AI/Dialog Systems

Application Category

• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

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.

Problem

• clustering
• customer support conversations
• multi-turn dialogues
• lifecycle-aware
• overlap concerns

Innovation

• LLM-guided clustering
• lifecycle-aware
• incremental clustering
• multi-turn conversation
• cluster quality monitoring