# QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation

arXiv: https://arxiv.org/abs/2406.00049 · HTML: https://mlsanity.com/paper/2406.00049/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 79 references that are in the map.
- First posted on arXiv 28 May 2024.

## Builds on (most cited first, 30 of 48)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning](https://mlsanity.com/paper/1910.00177/) (2019)
- [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://mlsanity.com/paper/2401.08417/) (2024)
- [Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation](https://mlsanity.com/paper/2106.04399/) (2021)
- [How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation](https://mlsanity.com/paper/2302.09210/) (2023)
- [Six Challenges for Neural Machine Translation](https://mlsanity.com/paper/1706.03872/) (2017)
- [Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models](https://mlsanity.com/paper/1610.02424/) (2016)
- [xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detection](https://mlsanity.com/paper/2310.10482/) (2023)
- [A Survey of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2312.14925/) (2023)
- [Tower: An Open Multilingual Large Language Model for Translation-Related Tasks](https://mlsanity.com/paper/2402.17733/) (2024)
- [BERT has a Mouth, and It Must Speak: BERT as a Markov Random Field Language Model](https://mlsanity.com/paper/1902.04094/) (2019)
- [COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics](https://mlsanity.com/paper/2202.11705/) (2022)
- [Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation](https://mlsanity.com/paper/2005.10283/) (2020)
- [RL with KL penalties is better viewed as Bayesian inference](https://mlsanity.com/paper/2205.11275/) (2022)
- [Hallucinations in Large Multilingual Translation Models](https://mlsanity.com/paper/2303.16104/) (2023)
- [Analyzing Uncertainty in Neural Machine Translation](https://mlsanity.com/paper/1803.00047/) (2018)
- [Aligning Language Models with Preferences through f-divergence Minimization](https://mlsanity.com/paper/2302.08215/) (2023)
- [Minimum Risk Training for Neural Machine Translation](https://mlsanity.com/paper/1512.02433/) (2015)
- [On NMT Search Errors and Model Errors: Cat Got Your Tongue?](https://mlsanity.com/paper/1908.10090/) (2019)
- [High Quality Rather than High Model Probability: Minimum Bayes Risk Decoding with Neural Metrics](https://mlsanity.com/paper/2111.09388/) (2021)
- [CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling](https://mlsanity.com/paper/1811.10996/) (2018)
- [Scaling up COMETKIWI: Unbabel-IST 2023 Submission for the Quality Estimation Shared Task](https://mlsanity.com/paper/2309.11925/) (2023)
- [Larger-Scale Transformers for Multilingual Masked Language Modeling](https://mlsanity.com/paper/2105.00572/) (2021)
- [Beyond BLEU: Training Neural Machine Translation with Semantic Similarity](https://mlsanity.com/paper/1909.06694/) (2019)
- [On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting](https://mlsanity.com/paper/2206.00761/) (2022)
- [Mixture Models for Diverse Machine Translation: Tricks of the Trade](https://mlsanity.com/paper/1902.07816/) (2019)
- [Mix and Match: Learning-free Controllable Text Generation using Energy Language Models](https://mlsanity.com/paper/2203.13299/) (2022)
- [Gradient-Based Constrained Sampling from Language Models](https://mlsanity.com/paper/2205.12558/) (2022)

## Built on by (most cited first, 16 of 16)

- [Reasoning with Sampling: Your Base Model is Smarter Than You Think](https://mlsanity.com/paper/2510.14901/) (2025)
- [Sample, Don't Search: Rethinking Test-Time Alignment for Language Models](https://mlsanity.com/paper/2504.03790/) (2025)
- [Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems](https://mlsanity.com/paper/2506.10060/) (2025)
- [Rare Event Analysis of Large Language Models](https://mlsanity.com/paper/2602.06791/) (2026)
- [The Geometric Reasoner: Manifold-Informed Latent Foresight Search for Long-Context Reasoning](https://mlsanity.com/paper/2601.18832/) (2026)
- [Reliable Chain-of-Thought via Prefix Consistency](https://mlsanity.com/paper/2605.07654/) (2026)
- [Drift is a Sampling Error: SNR-Aware Power Distributions for Long-Horizon Robotic Planning](https://mlsanity.com/paper/2605.09537/) (2026)
- [Calibrating Translation Decoding with Quality Estimation on LLMs](https://mlsanity.com/paper/2504.19044/) (2025)
- [BayesFlow: A Probability Inference Framework for Meta-Agent Assisted Workflow Generation](https://mlsanity.com/paper/2601.22305/) (2026)
- [Quality-Aware Decoding: Unifying Quality Estimation and Decoding](https://mlsanity.com/paper/2502.08561/) (2025)
- [STARS: Synchronous Token Alignment for Robust Supervision in Large Language Models](https://mlsanity.com/paper/2511.03827/) (2025)
- [In-Context Source and Channel Coding](https://mlsanity.com/paper/2601.10267/) (2026)
- [Depth-Entropy Guided Sampling for Training-Free LLM Reasoning](https://mlsanity.com/paper/2607.09693/) (2026)
- [Structured Inference with Large Language Gibbs](https://mlsanity.com/paper/2606.19264/) (2026)
- [Explore Broadly, Reason Sharply: Push Small Models toward the Frontier via Sampling](https://mlsanity.com/paper/2609.38104/) (2026)
- [Finetuning with Sampling: SFT Learns Better Than You Think](https://mlsanity.com/paper/2610.02140/) (2026)

## Abstract (arXiv)

An important challenge in machine translation (MT) is to generate high-quality and diverse translations. Prior work has shown that the estimated likelihood from the MT model correlates poorly with translation quality. In contrast, quality evaluation metrics (such as COMET or BLEURT) exhibit high correlations with human judgments, which has motivated their use as rerankers (such as quality-aware and minimum Bayes risk decoding). However, relying on a single translation with high estimated quality increases the chances of "gaming the metric''. In this paper, we address the problem of sampling a set of high-quality and diverse translations. We provide a simple and effective way to avoid over-reliance on noisy quality estimates by using them as the energy function of a Gibbs distribution. Instead of looking for a mode in the distribution, we generate multiple samples from high-density areas through the Metropolis-Hastings algorithm, a simple Markov chain Monte Carlo approach. The results show that our proposed method leads to high-quality and diverse outputs across multiple language pairs (EnglishleftrightarrowGerman, Russian) with two strong decoder-only LLMs (Alma-7b, Tower-7b).