# Epsilon Sampling Rocks: Investigating Sampling Strategies for Minimum Bayes Risk Decoding for Machine Translation

arXiv: https://arxiv.org/abs/2305.09860 · HTML: https://mlsanity.com/paper/2305.09860/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 40 references that are in the map.
- First posted on arXiv 17 May 2023.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [Convolutional Sequence to Sequence Learning](https://mlsanity.com/paper/1705.03122/) (2017)
- [Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translation](https://mlsanity.com/paper/2104.14478/) (2021)
- [Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation](https://mlsanity.com/paper/2005.10283/) (2020)
- [Truncation Sampling as Language Model Desmoothing](https://mlsanity.com/paper/2210.15191/) (2022)
- [BLEU might be Guilty but References are not Innocent](https://mlsanity.com/paper/2004.06063/) (2020)
- [High Quality Rather than High Model Probability: Minimum Bayes Risk Decoding with Neural Metrics](https://mlsanity.com/paper/2111.09388/) (2021)
- [A Statistical Analysis of Summarization Evaluation Metrics using Resampling Methods](https://mlsanity.com/paper/2104.00054/) (2021)
- [Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation](https://mlsanity.com/paper/2105.08504/) (2021)
- [Quality-Aware Decoding for Neural Machine Translation](https://mlsanity.com/paper/2205.00978/) (2022)
- [Denoising Neural Machine Translation Training with Trusted Data and Online Data Selection](https://mlsanity.com/paper/1809.00068/) (2018)
- [Identifying Weaknesses in Machine Translation Metrics Through Minimum Bayes Risk Decoding: A Case Study for COMET](https://mlsanity.com/paper/2202.05148/) (2022)
- [Learning to Evaluate Translation Beyond English: BLEURT Submissions to the WMT Metrics 2020 Shared Task](https://mlsanity.com/paper/2010.04297/) (2020)
- [Adam Mickiewicz University at WMT 2022: NER-Assisted and Quality-Aware Neural Machine Translation](https://mlsanity.com/paper/2209.02962/) (2022)

## Built on by (most cited first, 30 of 58)

- [From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models](https://mlsanity.com/paper/2406.16838/) (2024)
- [Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaboration](https://mlsanity.com/paper/2404.12715/) (2024)
- [Uncertainty in Natural Language Generation: From Theory to Applications](https://mlsanity.com/paper/2307.15703/) (2023)
- [It's MBR All the Way Down: Modern Generation Techniques Through the Lens of Minimum Bayes Risk](https://mlsanity.com/paper/2310.01387/) (2023)
- [Faster Minimum Bayes Risk Decoding with Confidence-based Pruning](https://mlsanity.com/paper/2311.14919/) (2023)
- [MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding Methods](https://mlsanity.com/paper/2309.10966/) (2023)
- [Closing the Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/2310.01693/) (2023)
- [Direct Preference Optimization for Neural Machine Translation with Minimum Bayes Risk Decoding](https://mlsanity.com/paper/2311.08380/) (2023)
- [Non-Exchangeable Conformal Language Generation with Nearest Neighbors](https://mlsanity.com/paper/2402.00707/) (2024)
- [Linear-time Minimum Bayes Risk Decoding with Reference Aggregation](https://mlsanity.com/paper/2402.04251/) (2024)
- [Better Instruction-Following Through Minimum Bayes Risk](https://mlsanity.com/paper/2410.02902/) (2024)
- [Narrowing the Knowledge Evaluation Gap: Open-Domain Question Answering with Multi-Granularity Answers](https://mlsanity.com/paper/2401.04695/) (2024)
- [QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation](https://mlsanity.com/paper/2406.00049/) (2024)
- [Mitigating Metric Bias in Minimum Bayes Risk Decoding](https://mlsanity.com/paper/2411.03524/) (2024)
- [Hyperparameter-Free Approach for Faster Minimum Bayes Risk Decoding](https://mlsanity.com/paper/2401.02749/) (2024)
- [Regression-aware Inference with LLMs](https://mlsanity.com/paper/2403.04182/) (2024)
- [Don't Rank, Combine! Combining Machine Translation Hypotheses Using Quality Estimation](https://mlsanity.com/paper/2401.06688/) (2024)
- [Efficient Minimum Bayes Risk Decoding using Low-Rank Matrix Completion Algorithms](https://mlsanity.com/paper/2406.02832/) (2024)
- [Improving Minimum Bayes Risk Decoding with Multi-Prompt](https://mlsanity.com/paper/2407.15343/) (2024)
- [Centroid-Based Efficient Minimum Bayes Risk Decoding](https://mlsanity.com/paper/2402.11197/) (2024)
- [Model-Based Minimum Bayes Risk Decoding for Text Generation](https://mlsanity.com/paper/2311.05263/) (2023)
- [Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decoding](https://mlsanity.com/paper/2401.05054/) (2024)
- [Introducing the NewsPaLM MBR and QE Dataset: LLM-Generated High-Quality Parallel Data Outperforms Traditional Web-Crawled Data](https://mlsanity.com/paper/2408.06537/) (2024)
- [Quality-Aware Translation Models: Efficient Generation and Quality Estimation in a Single Model](https://mlsanity.com/paper/2310.06707/) (2023)
- [Diversity Explains Inference Scaling Laws: Through a Case Study of Minimum Bayes Risk Decoding](https://mlsanity.com/paper/2410.15021/) (2024)
- [When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs](https://mlsanity.com/paper/2506.20544/) (2025)
- [Semantic-guided Diverse Decoding for Large Language Model](https://mlsanity.com/paper/2506.23601/) (2025)
- [Chasing COMET: Leveraging Minimum Bayes Risk Decoding for Self-Improving Machine Translation](https://mlsanity.com/paper/2405.11937/) (2024)
- [SpecFuse: Ensembling Large Language Models via Next-Segment Prediction](https://mlsanity.com/paper/2412.07380/) (2024)
- [Mitigating Hallucinated Translations in Large Language Models with Hallucination-focused Preference Optimization](https://mlsanity.com/paper/2501.17295/) (2025)

## Abstract (arXiv)

Recent advances in machine translation (MT) have shown that Minimum Bayes Risk (MBR) decoding can be a powerful alternative to beam search decoding, especially when combined with neural-based utility functions. However, the performance of MBR decoding depends heavily on how and how many candidates are sampled from the model. In this paper, we explore how different sampling approaches for generating candidate lists for MBR decoding affect performance. We evaluate popular sampling approaches, such as ancestral, nucleus, and top-k sampling. Based on our insights into their limitations, we experiment with the recently proposed epsilon-sampling approach, which prunes away all tokens with a probability smaller than epsilon, ensuring that each token in a sample receives a fair probability mass. Through extensive human evaluations, we demonstrate that MBR decoding based on epsilon-sampling significantly outperforms not only beam search decoding, but also MBR decoding with all other tested sampling methods across four language pairs.