@inproceedings{lee-etal-2025-mnlp,
    title = "{MNLP} at {P}er{A}ns{S}umm: A Classifier-Refiner Architecture for Improving the Classification of Consumer Health User Responses",
    author = {Lee, Jooyeon  and
      Pham, Luan  and
      Uzuner, {\"O}zlem},
    editor = "Ananiadou, Sophia  and
      Demner-Fushman, Dina  and
      Gupta, Deepak  and
      Thompson, Paul",
    booktitle = "Proceedings of the Second Workshop on Patient-Oriented Language Processing (CL4Health)",
    month = may,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.cl4health-1.31/",
    pages = "349--358",
    ISBN = "979-8-89176-238-1",
    abstract = "Community question-answering (CQA) platforms provide a crucial space for users to share experiences, seek medical advice, and exchange health-related information. However, these platforms, by nature of their user-generated content as well as the complexity and subjectivity of natural language, remain a significant challenge for tasks related to the automatic classification of diverse perspectives. The PerAnsSumm shared task involves extracting perspective spans from community users' answers, classifying them into specific perspective categories (Task A), and then using these perspectives and spans to generate structured summaries (Task B). Our focus is on Task A. To address this challenge, we propose a Classifier-Refiner Architecture (CRA), a two-stage framework designed to enhance classification accuracy. The first stage employs a Classifier to segment user responses into self-contained snippets and assign initial perspective labels along with a binary confidence value. If the classifier is not confident, a secondary Refiner stage is triggered, incorporating retrieval-augmented generation to enhance classification through contextual examples. Our methodology integrates instruction-driven classification, tone definitions, and Chain-of-Thought (CoT) prompting, leading to improved F1 scores compared to single-pass approaches. Experimental evaluations on the Perspective Summarization Dataset (PUMA) demonstrate that our framework improves classification performance by leveraging multi-stage decision-making. Our submission ranked among the top-performing teams, achieving an overall score of 0.6090, with high precision and recall in perspective classification."
}