@inproceedings{wu-etal-2025-incremental,
    title = "Incremental Summarization for Customer Support via Progressive Note-Taking and Agent Feedback",
    author = "Wu, Yisha  and
      Zhao, Cen  and
      Cao, Yuanpei  and
      Xu, Xiaoqing  and
      Mehdad, Yashar  and
      Ji, Mindy  and
      Cheng, Claire Na",
    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.140/",
    pages = "2000--2015",
    ISBN = "979-8-89176-333-3",
    abstract = "We introduce an incremental summarization system for customer support agents that intelligently determines when to generate concise bullet notes during conversations, reducing agents' cognitive load and redundant review. Our approach combines a fine-tuned Mixtral-8{\texttimes}7B model for continuous note generation with a DeBERTa-based classifier to filter trivial content. Agent edits refine the online notes generation and regularly inform offline model retraining, closing the agent edits feedback loop. Deployed in production, our system achieved a 3{\%} reduction in case handling time compared to bulk summarization (with reductions of up to 9{\%} in highly complex cases), alongside high agent satisfaction ratings from surveys. These results demonstrate that incremental summarization with continuous feedback effectively enhances summary quality and agent productivity at scale."
}