mlsanityData to 14 Oct 2026

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

arXiv 2503.21332 ↗First posted 27 Mar 2025cs.CL cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 41 of its 46 references that are in the map. First posted on arXiv 27 Mar 2025.

Builds on

41 of 46 references.

References · 41

  1. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  2. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
  3. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,122
  4. 2023Large Language Models are not Fair Evaluatorscited by 1,085
  5. 2016Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyondcited by 812
  6. 2020SummEval: Re-evaluating Summarization Evaluationcited by 674
  7. 2018A Discourse-Aware Attention Model for Abstractive Summarization of Long Documentscited by 478
  8. 2023Fine-Grained Human Feedback Gives Better Rewards for Language Model Trainingcited by 401
  9. 2021Efficient Attentions for Long Document Summarizationcited by 345
  10. 2025Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Modelscited by 293
  11. 2024MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documentscited by 257
  12. 2023REFINER: Reasoning Feedback on Intermediate Representationscited by 205
29 more
  1. 2018WikiHow: A Large Scale Text Summarization Datasetcited by 204
  2. 2023FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Setscited by 201
  3. 2020USR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generationcited by 188
  4. 2021DialogSum: A Real-Life Scenario Dialogue Summarization Datasetcited by 183
  5. 2024Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systemscited by 164
  6. 2024Evaluation of OpenAI o1: Opportunities and Challenges of AGIcited by 127
  7. 2024Controllable Preference Optimization: Toward Controllable Multi-Objective Alignmentcited by 107
  8. 2021MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarizationcited by 104
  9. 2023MeetingBank: A Benchmark Dataset for Meeting Summarizationcited by 84
  10. 2024FineSurE: Fine-grained Summarization Evaluation using LLMscited by 83
  11. 2024MathGenie: Generating Synthetic Data with Question Back-translation for Enhancing Mathematical Reasoning of LLMscited by 72
  12. 2024TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarizationcited by 66
  13. 2024A Comparative Study on Reasoning Patterns of OpenAI's o1 Modelcited by 63
  14. 2025RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?cited by 60
  15. 2023SummIt: Iterative Text Summarization via ChatGPTcited by 54
  16. 2023LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedbackcited by 39
  17. 2022On Improving Summarization Factual Consistency from Natural Language Feedbackcited by 38
  18. 2023The ART of LLM Refinement: Ask, Refine, and Trustcited by 29
  19. 2024Learning to Refine with Fine-Grained Natural Language Feedbackcited by 27
  20. 2024Learning to Summarize from LLM-generated Feedbackcited by 24
  21. 2024SPO: Multi-Dimensional Preference Sequential Alignment With Implicit Reward Modelingcited by 21
  22. 2024UniSumEval: Towards Unified, Fine-Grained, Multi-Dimensional Summarization Evaluation for LLMscited by 21
  23. 2024Batch-ICL: Effective, Efficient, and Order-Agnostic In-Context Learningcited by 20
  24. 2024Prompt Chaining or Stepwise Prompt? Refinement in Text Summarizationcited by 17
  25. 2022Improving Factual Consistency in Summarization with Compression-Based Post-Editingcited by 13
  26. 2024SYNFAC-EDIT: Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarizationcited by 12
  27. 2023Improving Factual Consistency of News Summarization by Contrastive Preference Optimizationcited by 6
  28. 2024Multi-Dimensional Optimization for Text Summarization via Reinforcement Learningcited by 6
  29. 2024CERET: Cost-Effective Extrinsic Refinement for Text Generationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2025Understanding LLM Reasoning for Abstractive Summarizationcited by 12
  2. 2026Learning to Control Summaries with Score Rankingcited by 4
  3. 2026When Does Context Help? Error Dynamics of Contextual Information in Large Language Modelscited by 0
  4. 2026Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decodingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026ReSum: Synergizing LLM Reasoning and Summarization with Reinforcement Learning
  2. 2025Retrieval Enhanced Feedback via In-context Neural Error-book
  3. 2025Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs
  4. 2025First Try Matters: Revisiting the Role of Reflection in Reasoning Models
  5. 2025RefineBench: Evaluating Refinement Capability of Language Models via Checklists
  6. 2024Teaching LLMs to Refine with Tools
  7. 2025ReflCtrl: Controlling LLM Reflection Efficiently via Representation Engineering
  8. 2024MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning