REIC: RAG-Enhanced Intent Classification at Scale

TL;DR

REIC introduces a retrieval-augmented generation method for scalable, accurate intent classification in customer service, outperforming traditional approaches and adaptable to large, evolving intent taxonomies.

Contribution

The paper presents REIC, a novel RAG-based approach that enhances intent classification scalability and accuracy without frequent retraining, suitable for large and diverse datasets.

Findings

REIC outperforms traditional fine-tuning, zero-shot, and few-shot methods.

Effective in both in-domain and out-of-domain scenarios.

Demonstrates potential for real-world large-scale deployment.

Abstract

Accurate intent classification is critical for efficient routing in customer service, ensuring customers are connected with the most suitable agents while reducing handling times and operational costs. However, as companies expand their product lines, intent classification faces scalability challenges due to the increasing number of intents and variations in taxonomy across different verticals. In this paper, we introduce REIC, a Retrieval-augmented generation Enhanced Intent Classification approach, which addresses these challenges effectively. REIC leverages retrieval-augmented generation (RAG) to dynamically incorporate relevant knowledge, enabling precise classification without the need for frequent retraining. Through extensive experiments on real-world datasets, we demonstrate that REIC outperforms traditional fine-tuning, zero-shot, and few-shot methods in large-scale customer service settings. Our results highlight its effectiveness in both in-domain and out-of-domain scenarios, demonstrating its potential for real-world deployment in adaptive and large-scale intent classification systems.