@inproceedings{chawla-etal-2026-lessons,
    title = "Lessons from the Field: An Adaptable Lifecycle Approach to Applied Dialogue Summarization",
    author = "Chawla, Kushal  and
      Zhu, Chenyang  and
      Cai, Pengshan  and
      Cho, Sangwoo  and
      Novotney, Scott  and
      Singh, Ayushman  and
      Lewis, Jonah  and
      Safewright, Keasha  and
      Samuel, Alfy  and
      Babinsky, Erin  and
      Zhang, Shi-Xiong  and
      Sahu, Sambit",
    editor = {Matusevych, Yevgen  and
      Eryi{\u{g}}it, G{\"u}l{\c{s}}en  and
      Aletras, Nikolaos},
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 5: Industry Track)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-industry.41/",
    pages = "535--544",
    ISBN = "979-8-89176-384-5",
    abstract = "Summarization of multi-party dialogues is a critical capability in industry, enhancing knowledge transfer and operational effectiveness across many domains. However, automatically generating high-quality summaries is challenging, as the ideal summary must satisfy a set of complex, multi-faceted requirements. While summarization has received immense attention in research, prior work has primarily utilized static datasets and benchmarks, a condition rare in practical scenarios where requirements inevitably evolve. In this work, we present an industry case study on developing an agentic system to summarize multi-party interactions. We share practical insights spanning the full development lifecycle to guide practitioners in building reliable, adaptable summarization systems, as well as to inform future research, covering: 1) robust methods for evaluation despite evolving requirements and task subjectivity, 2) component-wise optimization enabled by the task decomposition inherent in an agentic architecture, 3) the impact of upstream data bottlenecks, and 4) the realities of vendor lock-in due to the poor transferability of LLM prompts."
}