@inproceedings{pattnaik-etal-2025-scalable,
    title = "Scalable and Cost Effective High-Cardinality Classification with {LLM}s via Multi-View Label Representations and Retrieval Augmentation",
    author = "Pattnaik, Anup  and
      Vutla, Sasanka  and
      Dev, Hamvir  and
      Nandan, Jeevesh  and
      George, Cijo",
    editor = "Potdar, Saloni  and
      Rojas-Barahona, Lina  and
      Montella, Sebastien",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = nov,
    year = "2025",
    address = "Suzhou (China)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-industry.137/",
    pages = "1955--1969",
    ISBN = "979-8-89176-333-3",
    abstract = "Classifying contact center interactions into a large number of categories is critical for downstream analytics, but challenging due to high label cardinality, and cost constraints. While Large Language Models (LLMs) offer flexibility for such tasks, existing methods degrade with increasing label space, showing significant inconsistencies and sensitivity to label ordering. We propose a scalable, cost-effective two-step retrieval-augmented classification framework, enhanced with a multi-view representation of labels. Our method significantly improves accuracy and consistency over baseline LLM approaches. Experiments across 4 private and 5 open datasets yield performance improvements of upto 14.6{\%} while reducing inference cost by 60-91{\%} compared to baseline approaches."
}