mlsanityData to 7 Oct 2026

Machine Translation Decoding beyond Beam Search

arXiv 2104.05336 ↗First posted 12 Apr 2021cs.CL cs.LGcited by 55

Not on the map. Why?

Abstract (arXiv)

Beam search is the go-to method for decoding auto-regressive machine translation models. While it yields consistent improvements in terms of BLEU, it is only concerned with finding outputs with high model likelihood, and is thus agnostic to whatever end metric or score practitioners care about. Our aim is to establish whether beam search can be replaced by a more powerful metric-driven search technique. To this end, we explore numerous decoding algorithms, including some which rely on a value function parameterised by a neural network, and report results on a variety of metrics. Notably, we introduce a Monte-Carlo Tree Search (MCTS) based method and showcase its competitiveness. We provide a blueprint for how to use MCTS fruitfully in language applications, which opens promising future directions. We find that which algorithm is best heavily depends on the characteristics of the goal metric; we believe that our extensive experiments and analysis will inform further research in this area.

Key facts. Cited by 55 papers in the map (data through 7 Oct 2026). Builds on 30 of its 53 references that are in the map. First posted on arXiv 12 Apr 2021.

Builds on

30 of 53 references.

References · 30

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  5. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  6. 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,471
  7. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,327
  8. 2018Hierarchical Neural Story Generationcited by 1,182
  9. 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 779
  10. 2019Fast Transformer Decoding: One Write-Head is All You Needcited by 700
  11. 2015Sequence Level Training with Recurrent Neural Networkscited by 568
  12. 2017Non-Autoregressive Neural Machine Translationcited by 457
18 more
  1. 2019Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacementcited by 205
  2. 2016An Actor-Critic Algorithm for Sequence Predictioncited by 158
  3. 2020Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translationcited by 137
  4. 2015Minimum Risk Training for Neural Machine Translationcited by 114
  5. 2019On NMT Search Errors and Model Errors: Cat Got Your Tongue?cited by 114
  6. 2020If beam search is the answer, what was the question?cited by 114
  7. 2019On the Weaknesses of Reinforcement Learning for Neural Machine Translationcited by 82
  8. 2016Reward Augmented Maximum Likelihood for Neural Structured Predictioncited by 80
  9. 2017Classical Structured Prediction Losses for Sequence to Sequence Learningcited by 55
  10. 2019Non-Monotonic Sequential Text Generationcited by 55
  11. 2020Consistency of a Recurrent Language Model With Respect to Incomplete Decodingcited by 54
  12. 2020Energy-Based Reranking: Improving Neural Machine Translation Using Energy-Based Modelscited by 44
  13. 2020Best-First Beam Searchcited by 40
  14. 2017Deep Reinforcement Learning-based Image Captioning with Embedding Rewardcited by 39
  15. 2017SEARNN: Training RNNs with Global-Local Lossescited by 17
  16. 2019Leveraging Sentence Similarity in Natural Language Generation: Improving Beam Search using Range Votingcited by 15
  17. 2019A Fully Differentiable Beam Search Decodercited by 14
  18. 2020Investigating the Decoders of Maximum Likelihood Sequence Models: A Look-ahead Approachcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 12; 2023: 19; 2024: 9; 2025: 6; 2026: 2.

55 papers.

Sort:

By area:

  1. 2023Reinforced Self-Training (ReST) for Language Modelingcited by 486
  2. 2023Alphazero-like Tree-Search can Guide Large Language Model Decoding and Trainingcited by 291
  3. 2023Planning with Large Language Models for Code Generationcited by 179
  4. 2021NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristicscited by 153
  5. 2022Offline RL for Natural Language Generation with Implicit Language Q Learningcited by 137
  6. 2024Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decodingcited by 127
  7. 2021High Quality Rather than High Model Probability: Minimum Bayes Risk Decoding with Neural Metricscited by 104
  8. 2025Inference-Time Alignment in Diffusion Models with Reward-Guided Generation: Tutorial and Reviewcited by 82
  9. 2023Transformer-based Planning for Symbolic Regressioncited by 72
  10. 2023Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedbackcited by 71
  11. 2023Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agentscited by 66
  12. 2021Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translationcited by 63
38 more
  1. 2023Don't throw away your value model! Generating more preferable text with Value-Guided Monte-Carlo Tree Search decodingcited by 59
  2. 2023The Curious Case of Hallucinatory (Un)answerability: Finding Truths in the Hidden States of Over-Confident Large Language Modelscited by 54
  3. 2022Quality-Aware Decoding for Neural Machine Translationcited by 49
  4. 2024MegaAgent: A Large-Scale Autonomous LLM-based Multi-Agent System Without Predefined SOPscited by 45
  5. 2023KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detectioncited by 43
  6. 2023Tuning computer vision models with task rewardscited by 36
  7. 2025Dynamic Search for Inference-Time Alignment in Diffusion Modelscited by 36
  8. 2021PPL-MCTS: Constrained Textual Generation Through Discriminator-Guided MCTS Decodingcited by 32
  9. 2023Faithful Question Answering with Monte-Carlo Planningcited by 16
  10. 2025Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compressioncited by 15
  11. 2021To Beam Or Not To Beam: That is a Question of Cooperation for Language GANscited by 14
  12. 2024Don't Rank, Combine! Combining Machine Translation Hypotheses Using Quality Estimationcited by 13
  13. 2022Teacher Forcing Recovers Reward Functions for Text Generationcited by 11
  14. 2024Optimized Multi-Token Joint Decoding with Auxiliary Model for LLM Inferencecited by 11
  15. 2023R-U-SURE? Uncertainty-Aware Code Suggestions By Maximizing Utility Across Random User Intentscited by 10
  16. 2022Uncertainty Determines the Adequacy of the Mode and the Tractability of Decoding in Sequence-to-Sequence Modelscited by 9
  17. 2023Selective Perception: Optimizing State Descriptions with Reinforcement Learning for Language Model Actorscited by 9
  18. 2022Generative Cooperative Networks for Natural Language Generationcited by 8
  19. 2021BEAMetrics: A Benchmark for Language Generation Evaluation Evaluationcited by 6
  20. 2022Best-k Search Algorithm for Neural Text Generationcited by 6
  21. 2024Entropy-Reinforced Planning with Large Language Models for Drug Discoverycited by 6
  22. 2022Language Model Decoding as Likelihood-Utility Alignmentcited by 5
  23. 2022DC-MBR: Distributional Cooling for Minimum Bayesian Risk Decodingcited by 4
  24. 2023EEL: Efficiently Encoding Lattices for Rerankingcited by 4
  25. 2023The Inner Sentiments of a Thoughtcited by 4
  26. 2023K-pop Lyric Translation: Dataset, Analysis, and Neural-Modellingcited by 4
  27. 2024Uncertainty-Guided Likelihood Tree Searchcited by 4
  28. 2025Ontology-Guided, Hybrid Prompt Learning for Generalization in Knowledge Graph Question Answeringcited by 3
  29. 2025ScaffoldGPT: A Scaffold-based GPT Model for Drug Optimizationcited by 3
  30. 2021Digging Errors in NMT: Evaluating and Understanding Model Errors from Partial Hypothesis Spacecited by 2
  31. 2022RMBR: A Regularized Minimum Bayes Risk Reranking Framework for Machine Translationcited by 2
  32. 2022Which Discriminator for Cooperative Text Generation?cited by 2
  33. 2022Recurrent Convolutional Neural Networks Learn Succinct Learning Algorithmscited by 2
  34. 2023On the Depth between Beam Search and Exhaustive Search for Text Generationcited by 2
  35. 2025xGR: Efficient Generative Recommendation Serving at Scalecited by 2
  36. 2023Combining Language Models For Specialized Domains: A Colorful Approachcited by 1
  37. 2024When Only Time Will Tell: Interpreting How Transformers Process Local Ambiguities Through the Lens of Restart-Incrementalitycited by 1
  38. 2024Learning to Deliver: a Foundation Model for the Montreal Capacitated Vehicle Routing Problemcited by 1

50 most cited of 55 All 55 (JSON)