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

ytaewon, Jihwan Oh, Hyangsuk Min, Yuho Lee, Jihwan Bang, Jinglun (Jason) Cai, Hwanjun Song

ReFeed: Multi-dimensional Summarization Refinement with Reflective Reasoning on Feedback: 25 upvotes on Hugging Face Daily Papers, #8 of 23 papers on 2025-03-31. Day-by-day upvote history.

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.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.