@inproceedings{kirstein-etal-2025-frame,
    title = "Re-{FRAME} the Meeting Summarization {SCOPE}: Fact-Based Summarization and Personalization via Questions",
    author = "Kirstein, Frederic  and
      Kumar, Sonu  and
      Ruas, Terry  and
      Gipp, Bela",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.1094/",
    doi = "10.18653/v1/2025.findings-emnlp.1094",
    pages = "20087--20137",
    ISBN = "979-8-89176-335-7",
    abstract = "Meeting summarization with large language models (LLMs) remains error-prone, often producing outputs with hallucinations, omissions, and irrelevancies. We present FRAME, a modular pipeline that reframes summarization as a semantic enrichment task. FRAME extracts and scores salient facts, organizes them thematically, and uses these to enrich an outline into an abstractive summary. To personalize summaries, we introduce SCOPE, a reason-out-loud protocol that has the model build a reasoning trace by answering nine questions before content selection. For evaluation, we propose P-MESA, a multi-dimensional, reference-free evaluation framework to assess if a summary fits a target reader. P-MESA reliably identifies error instances, achieving $\geq 89%$ balanced accuracy against human annotations and strongly aligned with human severity ratings ($\rho \geq 0.70$). On QMSum and FAME, FRAME reduces hallucination and omission by 2 out of 5 points (measured with MESA), while SCOPE improves knowledge fit and goal alignment over prompt-only baselines. Our findings advocate for rethinking summarization to improve control, faithfulness, and personalization."
}