# Direct Preference Optimization for Neural Machine Translation with Minimum Bayes Risk Decoding

arXiv: https://arxiv.org/abs/2311.08380 · HTML: https://mlsanity.com/paper/2311.08380/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 16 of its 29 references that are in the map.
- First posted on arXiv 14 Nov 2023.

## Placed in

- LLM alignment / RLHF / preference optimisation / [LLM preference optimization methods](https://mlsanity.com/alignment/llm-preference-optimization-methods/)

## Builds on (most cited first, 16 of 16)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [GLM-130B: An Open Bilingual Pre-trained Model](https://mlsanity.com/paper/2210.02414/) (2022)
- [RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment](https://mlsanity.com/paper/2304.06767/) (2023)
- [Reinforced Self-Training (ReST) for Language Modeling](https://mlsanity.com/paper/2308.08998/) (2023)
- [Few-shot Learning with Multilingual Language Models](https://mlsanity.com/paper/2112.10668/) (2021)
- [The Tatoeba Translation Challenge -- Realistic Data Sets for Low Resource and Multilingual MT](https://mlsanity.com/paper/2010.06354/) (2020)
- [High Quality Rather than High Model Probability: Minimum Bayes Risk Decoding with Neural Metrics](https://mlsanity.com/paper/2111.09388/) (2021)
- [The unreasonable effectiveness of few-shot learning for machine translation](https://mlsanity.com/paper/2302.01398/) (2023)
- [Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation](https://mlsanity.com/paper/2108.04718/) (2021)
- [Epsilon Sampling Rocks: Investigating Sampling Strategies for Minimum Bayes Risk Decoding for Machine Translation](https://mlsanity.com/paper/2305.09860/) (2023)
- [Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk Decoding](https://mlsanity.com/paper/2211.07634/) (2022)
- [TIM: Teaching Large Language Models to Translate with Comparison](https://mlsanity.com/paper/2307.04408/) (2023)
- [MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding Methods](https://mlsanity.com/paper/2309.10966/) (2023)

## Built on by (most cited first, 28 of 28)

- [Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers](https://mlsanity.com/paper/2404.04925/) (2024)
- [Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing](https://mlsanity.com/paper/2406.05534/) (2024)
- [Regularized Best-of-N Sampling with Minimum Bayes Risk Objective for Language Model Alignment](https://mlsanity.com/paper/2404.01054/) (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)
- [Can Automatic Metrics Assess High-Quality Translations?](https://mlsanity.com/paper/2405.18348/) (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)
- [CycleVLA: Proactive Self-Correcting Vision-Language-Action Models via Subtask Backtracking and Minimum Bayes Risk Decoding](https://mlsanity.com/paper/2601.02295/) (2026)
- [Uncertainty-Aware Decoding with Minimum Bayes Risk](https://mlsanity.com/paper/2503.05318/) (2025)
- [On Extending Direct Preference Optimization to Accommodate Ties](https://mlsanity.com/paper/2409.17431/) (2024)
- [Modeling User Preferences with Automatic Metrics: Creating a High-Quality Preference Dataset for Machine Translation](https://mlsanity.com/paper/2410.07779/) (2024)
- [Cross-lingual Human-Preference Alignment for Neural Machine Translation with Direct Quality Optimization](https://mlsanity.com/paper/2409.17673/) (2024)
- [Is Preference Alignment Always the Best Option to Enhance LLM-Based Translation? An Empirical Analysis](https://mlsanity.com/paper/2409.20059/) (2024)
- [Advancing Decoding Strategies: Enhancements in Locally Typical Sampling for LLMs](https://mlsanity.com/paper/2506.05387/) (2025)
- [Annotation-Efficient Language Model Alignment via Diverse and Representative Response Texts](https://mlsanity.com/paper/2405.13541/) (2024)
- [CRPO: Confidence-Reward Driven Preference Optimization for Machine Translation](https://mlsanity.com/paper/2501.13927/) (2025)
- [On the True Distribution Approximation of Minimum Bayes-Risk Decoding](https://mlsanity.com/paper/2404.00752/) (2024)
- [Calibrating Translation Decoding with Quality Estimation on LLMs](https://mlsanity.com/paper/2504.19044/) (2025)
- [Structure-Conditional Minimum Bayes Risk Decoding](https://mlsanity.com/paper/2510.20700/) (2025)
- [Cross-Preference Learning for Sentence-Level and Context-Aware Machine Translation](https://mlsanity.com/paper/2603.25183/) (2026)
- [Minimum Bayes Risk Decoding for Error Span Detection in Reference-Free Automatic Machine Translation Evaluation](https://mlsanity.com/paper/2512.07540/) (2025)
- [Consensus Group Relative Policy Optimization for Text Generation](https://mlsanity.com/paper/2602.03102/) (2026)
- [STAR : Sentence Translation Alignment Rate for Document-to-Document Machine Translation](https://mlsanity.com/paper/2608.27161/) (2026)
- [PMMT: Preference Alignment in Multilingual Machine Translation via LLM Distillation](https://mlsanity.com/paper/2410.11410/) (2024)
- [Document-Level Text Generation with Minimum Bayes Risk Decoding using Optimal Transport](https://mlsanity.com/paper/2505.23078/) (2025)
- [BERAG: Bayesian Ensemble Retrieval-Augmented Generation for Knowledge-based Visual Question Answering](https://mlsanity.com/paper/2604.22678/) (2026)
- [Enhancing Small Language Models for Power Outage Report Generation via Minimum Risk Training](https://mlsanity.com/paper/2609.27197/) (2026)

## Abstract (arXiv)

Minimum Bayes Risk (MBR) decoding can significantly improve translation performance of Multilingual Large Language Models (MLLMs). However, MBR decoding is computationally expensive. We show how the recently developed Reinforcement Learning technique, Direct Preference Optimization (DPO), can fine-tune MLLMs to get the gains of MBR without any additional computation in inference. Our method uses only a small monolingual fine-tuning set and yields significantly improved performance on multiple NMT test sets compared to MLLMs without DPO.