Re-FRAME the Meeting Summarization SCOPE: Fact-Based Summarization and Personalization via Questions
This work addresses the problem of unreliable and non-personalized meeting summaries for users, presenting an incremental improvement with new methods for known bottlenecks.
The paper tackled the problem of error-prone meeting summarization with large language models by introducing FRAME, a modular pipeline that reframes summarization as semantic enrichment, and SCOPE, a personalization protocol, resulting in reduced hallucination and omission by 2 out of 5 points on benchmarks and achieving >= 89% balanced accuracy in evaluation.
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.