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

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

Keywords: Text Refinement, Text Summarization, LLMs, Reasoning

TL;DR: Reflective Reasoning for Text Refinement

Abstract: 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 is available at https://github.com/DISL-Lab/ReFeed.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 75