ReFeed：基於反饋反思推理的多維度摘要精煉

ReFeed: Multi-dimensional Summarization Refinement with Reflective Reasoning on Feedback

March 27, 2025

作者: Taewon Yun, Jihwan Oh, Hyangsuk Min, Yuho Lee, Jihwan Bang, Jason Cai, Hwanjun Song

cs.AI

摘要

在多維度擴展時，摘要精煉面臨挑戰。本文介紹了ReFeed，一個強大的摘要精煉流程，通過對反饋進行反思推理來增強多個維度。為實現這一目標，我們發布了SumFeed-CoT，這是一個大規模基於Long-CoT的數據集，專為訓練具有反思推理能力的輕量級模型而優化。我們的實驗揭示了維度數量、反饋暴露和推理策略如何影響精煉性能，強調了反思推理和同時處理多個反饋對於緩解維度間權衡的重要性。此外，ReFeed對噪聲反饋和反饋順序具有魯棒性。最後，我們的研究結果強調，創建具有適當目標和指南的數據是有效推理的基本支柱。數據集和模型將被公開。

English

Summarization refinement faces challenges when extending to multi-dimension. In this paper, we introduce ReFeed, a powerful summarization refinement pipeline that enhances multiple dimensions through reflective reasoning on feedback. To achieve this, we release SumFeed-CoT, a large-scale Long-CoT-based dataset optimized for training a lightweight model with reflective reasoning. Our experiments reveal how the number of dimensions, feedback exposure, and reasoning policy influence refinement performance, highlighting reflective reasoning and simultaneously addressing multiple feedback is crucial to mitigate trade-off between dimensions. Furthermore, ReFeed is robust to noisy feedback and feedback order. Lastly, our finding emphasizes that creating data with a proper goal and guideline constitutes a fundamental pillar of effective reasoning. The dataset and model will be released.