重构会议摘要SCOPE：基于问题的事实性摘要生成与个性化方法
Re-FRAME the Meeting Summarization SCOPE: Fact-Based Summarization and Personalization via Questions
AI总结：
针对大语言模型会议摘要易出现幻觉、遗漏等问题，提出FRAME事实性摘要流水线与SCOPE个性化协议，搭配无参考评估框架P-MESA，有效提升摘要忠实度与个性化适配效果。
摘要：
基于大语言模型（LLM）的会议摘要生成仍易出错，常产生包含幻觉、内容遗漏和无关信息的输出。我们提出FRAME，这是一种将摘要生成重构为语义丰富任务的模块化流水线：FRAME会提取显著事实并评分，按主题组织这些事实，再利用它们将大纲扩充为生成式摘要。为实现摘要个性化，我们引入SCOPE，这是一种出声思考协议，会让模型在内容选择前通过回答9个问题构建推理轨迹。评估方面，我们提出P-MESA，这是一个多维、无参考的评估框架，用于评估摘要是否适配目标读者；P-MESA可可靠识别错误实例，在人工标注对照下平衡准确率≥89%，且与人工严重程度评分高度对齐（r≥0.70）。在QMSum和FAME数据集上，FRAME将幻觉和遗漏问题降低了2/5分（采用MESA测量），同时SCOPE相比仅用提示的基线提升了知识适配度和目标对齐度。我们的研究结论倡导重新思考摘要生成范式，以提升可控性、忠实度和个性化水平。
英文摘要：
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 >= 89% balanced accuracy against human annotations and strongly aligns with human severity ratings (r >= 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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
