Saved in:
Bibliographic Details
Main Authors: Embar, Varsha, Shrivastava, Ritvik, Damodaran, Vinay, Mehlinger, Travis, Hsiao, Yu-Chung, Raghunathan, Karthik
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.19090
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917967758884864
author Embar, Varsha
Shrivastava, Ritvik
Damodaran, Vinay
Mehlinger, Travis
Hsiao, Yu-Chung
Raghunathan, Karthik
author_facet Embar, Varsha
Shrivastava, Ritvik
Damodaran, Vinay
Mehlinger, Travis
Hsiao, Yu-Chung
Raghunathan, Karthik
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_19090
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLM-Based Insight Extraction for Contact Center Analytics and Cost-Efficient Deployment
Embar, Varsha
Shrivastava, Ritvik
Damodaran, Vinay
Mehlinger, Travis
Hsiao, Yu-Chung
Raghunathan, Karthik
Computation and Language
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.
title LLM-Based Insight Extraction for Contact Center Analytics and Cost-Efficient Deployment
topic Computation and Language
url https://arxiv.org/abs/2503.19090