LLM-Based Insight Extraction for Contact Center Analytics and Cost-Efficient Deployment
By: Varsha Embar , Ritvik Shrivastava , Vinay Damodaran and more
Potential Business Impact:
Automates customer service calls, saving time and money.
Large Language Models have transformed the Contact Center industry, manifesting in enhanced self-service tools, streamlined administrative processes, and augmented agent productivity. This paper delineates our system that automates call driver generation, which serves as the foundation for tasks such as topic modeling, incoming call classification, trend detection, and FAQ generation, delivering actionable insights for contact center agents and administrators to consume. We present a cost-efficient LLM system design, with 1) a comprehensive evaluation of proprietary, open-weight, and fine-tuned models and 2) cost-efficient strategies, and 3) the corresponding cost analysis when deployed in production environments.
Similar Papers
From Staff Messages to Actionable Insights: A Multi-Stage LLM Classification Framework for Healthcare Analytics
Computation and Language
Organizes hospital messages to improve patient care.
An LLM-Based Approach for Insight Generation in Data Analysis
Artificial Intelligence
Finds hidden patterns in data automatically.
From Large to Super-Tiny: End-to-End Optimization for Cost-Efficient LLMs
Computation and Language
Makes smart computer programs cheaper and faster.