mlsanityData to 14 Oct 2026

Enhancing Factuality through Consensus and Consistency in Summarization Using Minimum Bayes Risk Decoding

arXiv 2605.29336 ↗First posted 28 May 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Improving the quality of model-generated summaries, especially factuality, the accuracy of a summary with respect to its source content, remains a challenge. While reranking could select the optimal output from multiple generated candidates, it is limited to only using the source as guidance, resulting in unreliable summaries. To address this limitation, we propose ConSUM that reranks candidate summaries by considering two factors: consistency to the source document and consensus among the other candidates. Consensus is established using Minimum Bayes Risk (MBR) decoding over the set of generated summaries, while ensuring consistency by employing factuality-aware metrics that compare the summary against the source. Rigorous testing demonstrates that our system is competitive with existing methods, with human evaluations further confirming that its generated summaries are preferred over those from other systems. Our code is available at https://github.com/naist-nlp/ConSUM .

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 41 references that are in the map. First posted on arXiv 28 May 2026.

Builds on

30 of 41 references.

References · 30

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  3. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  4. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  5. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,181
  6. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,317
  7. 2019PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarizationcited by 1,102
  8. 2016Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyondcited by 812
  9. 2020SummEval: Re-evaluating Summarization Evaluationcited by 674
  10. 2023Benchmarking Large Language Models for News Summarizationcited by 445
  11. 2019MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distancecited by 418
  12. 2016Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Modelscited by 301
18 more
  1. 2022Towards a Unified Multi-Dimensional Evaluator for Text Generationcited by 264
  2. 2021SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarizationcited by 132
  3. 2022Truncation Sampling as Language Model Desmoothingcited by 123
  4. 2022SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive Summarizationcited by 61
  5. 2021Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translationcited by 56
  6. 2022Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk Decodingcited by 54
  7. 2023It's MBR All the Way Down: Modern Generation Techniques Through the Lens of Minimum Bayes Riskcited by 51
  8. 2022On Improving Summarization Factual Consistency from Natural Language Feedbackcited by 38
  9. 2023Faster Minimum Bayes Risk Decoding with Confidence-based Pruningcited by 34
  10. 2024Revisiting Zero-Shot Abstractive Summarization in the Era of Large Language Models from the Perspective of Position Biascited by 28
  11. 2024FENICE: Factuality Evaluation of summarization based on Natural language Inference and Claim Extractioncited by 28
  12. 2024Mitigating Metric Bias in Minimum Bayes Risk Decodingcited by 16
  13. 2024FIZZ: Factual Inconsistency Detection by Zoom-in Summary and Zoom-out Documentcited by 15
  14. 2024Efficient Minimum Bayes Risk Decoding using Low-Rank Matrix Completion Algorithmscited by 13
  15. 2024mbrs: A Library for Minimum Bayes Risk Decodingcited by 13
  16. 2024Diversity Explains Inference Scaling Laws: Through a Case Study of Minimum Bayes Risk Decodingcited by 9
  17. 2023Improving Factuality of Abstractive Summarization without Sacrificing Summary Qualitycited by 7
  18. 2025Agreement-Constrained Probabilistic Minimum Bayes Risk Decodingcited by 2

Built on by

Not cited yet.