通过反思反馈实现多维度摘要优化，解决维度间权衡难题。
ReFeed: Multi-dimensional Summarization Refinement with Reflective Reasoning on Feedback
- 基于反馈进行反思推理，同步优化多个摘要维度。
- 实验表明，多维度与反馈暴露量提升显著改善生成质量。
- 对噪声和顺序不敏感，适合实际应用中复杂反馈场景。
摘要精炼在扩展至多维度时面临挑战。本文提出ReFeed，一种通过反思反馈实现多维度增强的摘要精炼流水线。为此，我们发布了SumFeed-CoT——一个基于长思维链的大规模数据集，用于训练具备反思推理能力的轻量级模型。实验揭示了维度数量、反馈暴露程度及推理策略对精炼效果的影响，强调反思推理与同时处理多重反馈是缓解维度间权衡的关键。此外，ReFeed对噪声反馈和反馈顺序具有鲁棒性。研究还指出，设计目标明确、指导清晰的数据是有效推理的基础。相关数据集与模型将公开发布。
原文摘要 · Abstract (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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。