mlsanityData to 7 Oct 2026

Correcting Length Bias in Neural Machine Translation

arXiv 1808.10006 ↗First posted 29 Aug 2018cs.CLcited by 119

Not on the map. Why?

Abstract (arXiv)

We study two problems in neural machine translation (NMT). First, in beam search, whereas a wider beam should in principle help translation, it often hurts NMT. Second, NMT has a tendency to produce translations that are too short. Here, we argue that these problems are closely related and both rooted in label bias. We show that correcting the brevity problem almost eliminates the beam problem; we compare some commonly-used methods for doing this, finding that a simple per-word reward works well; and we introduce a simple and quick way to tune this reward using the perceptron algorithm.

Key facts. Cited by 119 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 2; 2021: 17; 2022: 18; 2023: 20; 2024: 21; 2025: 18; 2026: 23.

119 papers.

Sort:

By area:

  1. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 795
  2. 2023Robots That Ask For Help: Uncertainty Alignment for Large Language Model Plannerscited by 298
  3. 2023A Long Way to Go: Investigating Length Correlations in RLHFcited by 285
  4. 2023A Survey of Confidence Estimation and Calibration in Large Language Modelscited by 253
  5. 2024Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMscited by 246
  6. 2022Exploring Length Generalization in Large Language Modelscited by 204
  7. 2021Constrained Language Models Yield Few-Shot Semantic Parserscited by 162
  8. 2025Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMscited by 162
  9. 2024From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Modelscited by 136
  10. 2023End-to-End Speech Recognition: A Surveycited by 127
  11. 2022Pretrained Language Models for Text Generation: A Surveycited by 121
  12. 2024Language Model Cascades: Token-level uncertainty and beyondcited by 115
38 more
  1. 2023StarVector: Generating Scalable Vector Graphics Code from Images and Textcited by 96
  2. 2022On Decoding Strategies for Neural Text Generatorscited by 89
  3. 2022PEER: A Collaborative Language Modelcited by 86
  4. 2023Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programscited by 79
  5. 2024LUQ: Long-text Uncertainty Quantification for LLMscited by 79
  6. 2021Language Model Evaluation Beyond Perplexitycited by 77
  7. 2022Sequence-to-Sequence Knowledge Graph Completion and Question Answeringcited by 75
  8. 2020Text Generation by Learning from Demonstrationscited by 64
  9. 2023Length Generalization in Arithmetic Transformerscited by 64
  10. 2021Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translationcited by 63
  11. 2021A Plug-and-Play Method for Controlled Text Generationcited by 55
  12. 2022Quality-Aware Decoding for Neural Machine Translationcited by 49
  13. 2023It's MBR All the Way Down: Modern Generation Techniques Through the Lens of Minimum Bayes Riskcited by 49
  14. 2023Uncertainty in Natural Language Processing: Sources, Quantification, and Applicationscited by 44
  15. 2024A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMscited by 35
  16. 2022The Tail Wagging the Dog: Dataset Construction Biases of Social Bias Benchmarkscited by 31
  17. 2024Post-hoc Reward Calibration: A Case Study on Length Biascited by 29
  18. 2022CTC Alignments Improve Autoregressive Translationcited by 25
  19. 2021Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Taskscited by 24
  20. 2025TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoningcited by 24
  21. 2025Fast Controlled Generation from Language Models with Adaptive Weighted Rejection Samplingcited by 20
  22. 2025Reliable Text-to-SQL with Adaptive Abstentioncited by 19
  23. 2024Rethinking Uncertainty Estimation in LLMs: A Principled Single-Sequence Measurecited by 18
  24. 2025LoVeC: Reinforcement Learning for Better Verbalized Confidence in Long-Form Generationscited by 17
  25. 2025CER: Confidence Enhanced Reasoning in LLMscited by 16
  26. 2025Causal Estimation of Tokenisation Biascited by 16
  27. 2023Formally Specifying the High-Level Behavior of LLM-Based Agentscited by 15
  28. 2024UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Modelscited by 13
  29. 2026WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoningcited by 12
  30. 2021Smoothing and Shrinking the Sparse Seq2Seq Search Spacecited by 11
  31. 2025LLM Microscope: What Model Internals Reveal About Answer Correctness and Context Utilizationcited by 11
  32. 2020Learning Coupled Policies for Simultaneous Machine Translation using Imitation Learningcited by 10
  33. 2021Characterizing and addressing the issue of oversmoothing in neural autoregressive sequence modelingcited by 10
  34. 2022A Call for Clarity in Beam Search: How It Works and When It Stopscited by 10
  35. 2022Jam or Cream First? Modeling Ambiguity in Neural Machine Translation with SCONEScited by 10
  36. 2023Model-Based Minimum Bayes Risk Decoding for Text Generationcited by 10
  37. 2022Uncertainty Determines the Adequacy of the Mode and the Tractability of Decoding in Sequence-to-Sequence Modelscited by 9
  38. 2024Accelerating Multilingual Language Model for Excessively Tokenized Languagescited by 8

50 most cited of 119 All 119 (JSON)