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

• URL: http://arxiv.org/abs/2605.29336v1
• Date: Thu, 28 May 2026 04:14:43 GMT
• Title: Enhancing Factuality through Consensus and Consistency in Summarization Using Minimum Bayes Risk Decoding
• Abstract summary: We propose ConSUM that reranks candidate summaries by considering two factors: consistency to the source document and consensus among the other candidates.<n>Our system is competitive with existing methods, with human evaluations confirming that its generated summaries are preferred over those from other systems.
• Score: 64.98167175790817
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 .

Related papers

• Decoupling Generation and Selection for Budget-Constrained Faithful Summarization [5.708600866689601]
  We propose a modular generation-and-selection framework for sentence-budget-constrained summarization.<n>A pretrained generator produces multiple candidate summaries, which are decomposed into sentence-level candidates.<n>A selector then constructs the final summary by balancing relevance, factuality, and redundancy under an explicit budget.
  arXiv  Detail & Related papers  (2026-08-04T13:36:25Z)
• Faithful by Construction: Claim-Anchored Attribution for Multi-Document Summarization [1.1168121941015015]
  Claim-Anchored Multi-document Summarization framework ( CAMS)<n>Claim-Anchored Multi-document Summarization framework ( CAMS)
  arXiv  Detail & Related papers  (2026-06-22T22:39:08Z)
• Evaluating Code Summarization Techniques: A New Metric and an Empirical Characterization [16.127739014966487]
  We investigate the complementarity of different types of metrics in capturing the quality of a generated summary. We present a new metric based on contrastive learning to capture said aspect.
  arXiv  Detail & Related papers  (2023-12-24T13:12:39Z)
• AMRFact: Enhancing Summarization Factuality Evaluation with AMR-Driven Negative Samples Generation [57.8363998797433]
  We propose AMRFact, a framework that generates perturbed summaries using Abstract Meaning Representations (AMRs) Our approach parses factually consistent summaries into AMR graphs and injects controlled factual inconsistencies to create negative examples, allowing for coherent factually inconsistent summaries to be generated with high error-type coverage.
  arXiv  Detail & Related papers  (2023-11-16T02:56:29Z)
• MQAG: Multiple-choice Question Answering and Generation for Assessing Information Consistency in Summarization [55.60306377044225]
  State-of-the-art summarization systems can generate highly fluent summaries. These summaries, however, may contain factual inconsistencies and/or information not present in the source. We introduce an alternative scheme based on standard information-theoretic measures in which the information present in the source and summary is directly compared.
  arXiv  Detail & Related papers  (2023-01-28T23:08:25Z)
• Evaluating and Improving Factuality in Multimodal Abstractive Summarization [91.46015013816083]
  We propose CLIPBERTScore to leverage the robustness and strong factuality detection performance between image-summary and document-summary. We show that this simple combination of two metrics in the zero-shot achieves higher correlations than existing factuality metrics for document summarization. Our analysis demonstrates the robustness and high correlation of CLIPBERTScore and its components on four factuality metric-evaluation benchmarks.
  arXiv  Detail & Related papers  (2022-11-04T16:50:40Z)
• Masked Summarization to Generate Factually Inconsistent Summaries for Improved Factual Consistency Checking [28.66287193703365]
  We propose to generate factually inconsistent summaries using source texts and reference summaries with key information masked. Experiments on seven benchmark datasets demonstrate that factual consistency classifiers trained on summaries generated using our method generally outperform existing models.
  arXiv  Detail & Related papers  (2022-05-04T12:48:49Z)
• Investigating Crowdsourcing Protocols for Evaluating the Factual Consistency of Summaries [59.27273928454995]
  Current pre-trained models applied to summarization are prone to factual inconsistencies which misrepresent the source text or introduce extraneous information. We create a crowdsourcing evaluation framework for factual consistency using the rating-based Likert scale and ranking-based Best-Worst Scaling protocols. We find that ranking-based protocols offer a more reliable measure of summary quality across datasets, while the reliability of Likert ratings depends on the target dataset and the evaluation design.
  arXiv  Detail & Related papers  (2021-09-19T19:05:00Z)
• Uncertainty-Aware Abstractive Summarization [3.1423034006764965]
  We propose a novel approach to summarization based on Bayesian deep learning. We show that our variational equivalents of BART and PEG can outperform their deterministic counterparts on multiple benchmark datasets. Having a reliable uncertainty measure, we can improve the experience of the end user by filtering generated summaries of high uncertainty.
  arXiv  Detail & Related papers  (2021-05-21T06:36:40Z)
• Multi-Fact Correction in Abstractive Text Summarization [98.27031108197944]
  Span-Fact is a suite of two factual correction models that leverages knowledge learned from question answering models to make corrections in system-generated summaries via span selection. Our models employ single or multi-masking strategies to either iteratively or auto-regressively replace entities in order to ensure semantic consistency w.r.t. the source text. Experiments show that our models significantly boost the factual consistency of system-generated summaries without sacrificing summary quality in terms of both automatic metrics and human evaluation.
  arXiv  Detail & Related papers  (2020-10-06T02:51:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.