mlsanityData to 7 Oct 2026

Model-Based Minimum Bayes Risk Decoding for Text Generation

arXiv 2311.05263 ↗First posted 9 Nov 2023cs.AI cs.CLcited by 10

Not on the map. Why?

Abstract (arXiv)

Minimum Bayes Risk (MBR) decoding has been shown to be a powerful alternative to beam search decoding in a variety of text generation tasks. MBR decoding selects a hypothesis from a pool of hypotheses that has the least expected risk under a probability model according to a given utility function. Since it is impractical to compute the expected risk exactly over all possible hypotheses, two approximations are commonly used in MBR. First, it integrates over a sampled set of hypotheses rather than over all possible hypotheses. Second, it estimates the probability of each hypothesis using a Monte Carlo estimator. While the first approximation is necessary to make it computationally feasible, the second is not essential since we typically have access to the model probability at inference time. We propose Model-Based MBR (MBMBR), a variant of MBR that uses the model probability itself as the estimate of the probability distribution instead of the Monte Carlo estimate. We show analytically and empirically that the model-based estimate is more promising than the Monte Carlo estimate in text generation tasks. Our experiments show that MBMBR outperforms MBR in several text generation tasks, both with encoder-decoder models and with large language models.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 37 of its 62 references that are in the map. First posted on arXiv 9 Nov 2023.

Builds on

37 of 62 references.

References · 37

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  3. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  4. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  5. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  6. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  7. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
  8. 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,471
  9. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,308
  10. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,196
  11. 2018Hierarchical Neural Story Generationcited by 1,182
  12. 2015Teaching Machines to Read and Comprehendcited by 1,039
25 more
  1. 2019SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarizationcited by 530
  2. 2018nocaps: novel object captioning at scalecited by 444
  3. 2015A Neural Attention Model for Abstractive Sentence Summarizationcited by 394
  4. 2017Six Challenges for Neural Machine Translationcited by 334
  5. 2017The E2E Dataset: New Challenges For End-to-End Generationcited by 252
  6. 2019Facebook FAIR's WMT19 News Translation Task Submissioncited by 179
  7. 2020Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translationcited by 137
  8. 2022Truncation Sampling as Language Model Desmoothingcited by 121
  9. 2018Correcting Length Bias in Neural Machine Translationcited by 119
  10. 2019On NMT Search Errors and Model Errors: Cat Got Your Tongue?cited by 114
  11. 2020If beam search is the answer, what was the question?cited by 114
  12. 2016Guided Open Vocabulary Image Captioning with Constrained Beam Searchcited by 105
  13. 2021High Quality Rather than High Model Probability: Minimum Bayes Risk Decoding with Neural Metricscited by 104
  14. 2021Learning Compact Metrics for MTcited by 93
  15. 2023A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Modelscited by 88
  16. 2021Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translationcited by 63
  17. 2023Epsilon Sampling Rocks: Investigating Sampling Strategies for Minimum Bayes Risk Decoding for Machine Translationcited by 57
  18. 2020Unbabel's Participation in the WMT20 Metrics Shared Taskcited by 56
  19. 2021Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translationcited by 56
  20. 2020Consistency of a Recurrent Language Model With Respect to Incomplete Decodingcited by 54
  21. 2022Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk Decodingcited by 54
  22. 2022Quality-Aware Decoding for Neural Machine Translationcited by 49
  23. 2023It's MBR All the Way Down: Modern Generation Techniques Through the Lens of Minimum Bayes Riskcited by 49
  24. 2023MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding Methodscited by 33
  25. 2023An Empirical Study of Translation Hypothesis Ensembling with Large Language Modelscited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 3; 2026: 3.

10 papers.

  1. 2024mbrs: A Library for Minimum Bayes Risk Decodingcited by 13
  2. 2024Diversity Explains Inference Scaling Laws: Through a Case Study of Minimum Bayes Risk Decodingcited by 8
  3. 2025Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMscited by 5
  4. 2024On the True Distribution Approximation of Minimum Bayes-Risk Decodingcited by 2
  5. 2025Re-evaluating Minimum Bayes Risk Decoding for Automatic Speech Recognitioncited by 2
  6. 2026Uncertainty-Aware Generation and Decision-Making Under Ambiguitycited by 1
  7. 2024Exploring the traditional NMT model and Large Language Model for chat translationcited by 0
  8. 2025Document-Level Text Generation with Minimum Bayes Risk Decoding using Optimal Transportcited by 0
  9. 2026Overfitting Mitigation via Singular Value Decomposition in Minimum Bayes Risk Decodingcited by 0
  10. 2026Do Large Language Models Capture the Diversity in their Training Data?cited by 0