mlsanityData to 7 Oct 2026

Hyperparameter-Free Approach for Faster Minimum Bayes Risk Decoding

arXiv 2401.02749 ↗First posted 5 Jan 2024cs.AI cs.CLcited by 15

Not on the map. Why?

Abstract (arXiv)

Minimum Bayes-Risk (MBR) decoding is shown to be a powerful alternative to beam search decoding for a wide range of text generation tasks. However, MBR requires a huge amount of time for inference to compute the MBR objective, which makes the method infeasible in many situations where response time is critical. Confidence-based pruning (CBP) (Cheng and Vlachos, 2023) has recently been proposed to reduce the inference time in machine translation tasks. Although it is shown to significantly reduce the amount of computation, it requires hyperparameter tuning using a development set to be effective. To this end, we propose Approximate Minimum Bayes-Risk (AMBR) decoding, a hyperparameter-free method to run MBR decoding approximately. AMBR is derived from the observation that the problem of computing the sample-based MBR objective is the medoid identification problem. AMBR uses the Correlated Sequential Halving (CSH) algorithm (Baharav and Tse, 2019), the best approximation algorithm to date for the medoid identification problem, to compute the sample-based MBR objective. We evaluate AMBR on machine translation, text summarization, and image captioning tasks. The results show that AMBR achieves on par with CBP, with CBP selecting hyperparameters through an Oracle for each given computation budget.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 46 of its 69 references that are in the map. First posted on arXiv 5 Jan 2024.

Builds on

46 of 69 references.

References · 46

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  6. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  7. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  8. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  9. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  10. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  11. 2020Learning to summarize from human feedbackcited by 2,562
  12. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
34 more
  1. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  2. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
  3. 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,471
  4. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,308
  5. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,196
  6. 2023OpenAssistant Conversations -- Democratizing Large Language Model Alignmentcited by 712
  7. 2020Beyond English-Centric Multilingual Machine Translationcited by 559
  8. 2019SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarizationcited by 530
  9. 2015A Neural Attention Model for Abstractive Sentence Summarizationcited by 394
  10. 2021Understanding Dataset Difficulty with V-Usable Informationcited by 288
  11. 2014On the Complexity of Best Arm Identification in Multi-Armed Bandit Modelscited by 280
  12. 2020Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translationcited by 137
  13. 2022Truncation Sampling as Language Model Desmoothingcited by 121
  14. 2019On NMT Search Errors and Model Errors: Cat Got Your Tongue?cited by 114
  15. 2020If beam search is the answer, what was the question?cited by 114
  16. 2016Guided Open Vocabulary Image Captioning with Constrained Beam Searchcited by 105
  17. 2021High Quality Rather than High Model Probability: Minimum Bayes Risk Decoding with Neural Metricscited by 104
  18. 2021Learning Compact Metrics for MTcited by 93
  19. 2016Tight (Lower) Bounds for the Fixed Budget Best Arm Identification Bandit Problemcited by 79
  20. 2018What Doubling Tricks Can and Can't Do for Multi-Armed Banditscited by 69
  21. 2021Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translationcited by 63
  22. 2021Facebook AI WMT21 News Translation Task Submissioncited by 57
  23. 2023Epsilon Sampling Rocks: Investigating Sampling Strategies for Minimum Bayes Risk Decoding for Machine Translationcited by 57
  24. 2020Unbabel's Participation in the WMT20 Metrics Shared Taskcited by 56
  25. 2021Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translationcited by 56
  26. 2020Consistency of a Recurrent Language Model With Respect to Incomplete Decodingcited by 54
  27. 2023It's MBR All the Way Down: Modern Generation Techniques Through the Lens of Minimum Bayes Riskcited by 49
  28. 2022Identifying Weaknesses in Machine Translation Metrics Through Minimum Bayes Risk Decoding: A Case Study for COMETcited by 41
  29. 2023Faster Minimum Bayes Risk Decoding with Confidence-based Pruningcited by 34
  30. 2021InfoLM: A New Metric to Evaluate Summarization & Data2Text Generationcited by 33
  31. 2023MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding Methodscited by 33
  32. 2023Direct Preference Optimization for Neural Machine Translation with Minimum Bayes Risk Decodingcited by 28
  33. 2017Medoids in almost linear time via multi-armed banditscited by 10
  34. 2019Ultra Fast Medoid Identification via Correlated Sequential Halvingcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 5; 2026: 2.

15 papers.

Sort:

By area:

  1. 2024From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Modelscited by 136
  2. 2024Regularized Best-of-N Sampling with Minimum Bayes Risk Objective for Language Model Alignmentcited by 24
  3. 2024Linear-time Minimum Bayes Risk Decoding with Reference Aggregationcited by 21
  4. 2024Mitigating Metric Bias in Minimum Bayes Risk Decodingcited by 15
  5. 2024Efficient Minimum Bayes Risk Decoding using Low-Rank Matrix Completion Algorithmscited by 13
  6. 2024Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decodingcited by 11
  7. 2024Introducing the NewsPaLM MBR and QE Dataset: LLM-Generated High-Quality Parallel Data Outperforms Traditional Web-Crawled Datacited by 10
  8. 2026Test-Time Scaling in Reasoning LLMs: Inference Regimes, Evaluation, and Reproducibilitycited by 4
  9. 2025Theoretical Guarantees for Minimum Bayes Risk Decodingcited by 3
  10. 2024On the True Distribution Approximation of Minimum Bayes-Risk Decodingcited by 2
  11. 2025Re-evaluating Minimum Bayes Risk Decoding for Automatic Speech Recognitioncited by 2
  12. 2025Agreement-Constrained Probabilistic Minimum Bayes Risk Decodingcited by 2
3 more
  1. 2025Case-Based Decision-Theoretic Decoding with Quality Memoriescited by 1
  2. 2025Document-Level Text Generation with Minimum Bayes Risk Decoding using Optimal Transportcited by 0
  3. 2026Quit While You're Ahead: Quit for Efficient Candidate Generation in Machine Translation Rerankingcited by 0