mlsanityData to 7 Oct 2026

Can Neural Machine Translation be Improved with User Feedback?

arXiv 1804.05958 ↗First posted 16 Apr 2018cs.CL stat.MLcited by 71

Not on the map. Why?

Cited by 32 in LLM alignment / RLHF / preference optimisation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present the first real-world application of methods for improving neural machine translation (NMT) with human reinforcement, based on explicit and implicit user feedback collected on the eBay e-commerce platform. Previous work has been confined to simulation experiments, whereas in this paper we work with real logged feedback for offline bandit learning of NMT parameters. We conduct a thorough analysis of the available explicit user judgments---five-star ratings of translation quality---and show that they are not reliable enough to yield significant improvements in bandit learning. In contrast, we successfully utilize implicit task-based feedback collected in a cross-lingual search task to improve task-specific and machine translation quality metrics.

Key facts. Cited by 71 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2018: 1; 2019: 0; 2020: 2; 2021: 9; 2022: 6; 2023: 28; 2024: 19; 2025: 6.

71 papers.

Sort:

By area:

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2020Learning to summarize from human feedbackcited by 2,562
  3. 2023ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generationcited by 1,010
  4. 2023AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedbackcited by 738
  5. 2023Aligning Text-to-Image Models using Human Feedbackcited by 418
  6. 2024Humans or LLMs as the Judge? A Study on Judgement Biasescited by 314
  7. 2021Recursively Summarizing Books with Human Feedbackcited by 287
  8. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiescited by 236
  9. 2023RAIN: Your Language Models Can Align Themselves without Finetuningcited by 149
  10. 2023Chain of Hindsight Aligns Language Models with Feedbackcited by 147
  11. 2023DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedbackcited by 99
  12. 2024RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMscited by 89
38 more
  1. 2018Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learningcited by 57
  2. 2023Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generationcited by 55
  3. 2023Learning to Generate Better Than Your LLMcited by 49
  4. 2023Everyone Deserves A Reward: Learning Customized Human Preferencescited by 42
  5. 2021Putting Humans in the Natural Language Processing Loop: A Surveycited by 40
  6. 2024Curry-DPO: Enhancing Alignment using Curriculum Learning & Ranked Preferencescited by 39
  7. 2024M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitionscited by 38
  8. 2023Tuning computer vision models with task rewardscited by 36
  9. 2024Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Modelcited by 33
  10. 2024EffiLearner: Enhancing Efficiency of Generated Code via Self-Optimizationcited by 28
  11. 2023Aligning Language Models with Human Preferences via a Bayesian Approachcited by 27
  12. 2023Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Gamecited by 27
  13. 2021Reliability Testing for Natural Language Processing Systemscited by 25
  14. 2024HumanEvalComm: Benchmarking the Communication Competence of Code Generation for LLMs and LLM Agentcited by 24
  15. 2022Continual Learning for Instruction Following from Realtime Feedbackcited by 21
  16. 2021Continual Learning for Grounded Instruction Generation by Observing Human Following Behaviorcited by 19
  17. 2023Sample Efficient Preference Alignment in LLMs via Active Explorationcited by 18
  18. 2023Privately Aligning Language Models with Reinforcement Learningcited by 17
  19. 2021Modelling Latent Translations for Cross-Lingual Transfercited by 16
  20. 2021Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Banditscited by 16
  21. 2021Diversity driven Query Rewriting in Search Advertisingcited by 14
  22. 2022Simulating Bandit Learning from User Feedback for Extractive Question Answeringcited by 14
  23. 2025Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challengescited by 14
  24. 2024Advancing Translation Preference Modeling with RLHF: A Step Towards Cost-Effective Solutioncited by 13
  25. 2020Offline Reinforcement Learning from Human Feedback in Real-World Sequence-to-Sequence Taskscited by 12
  26. 2023ChatGPT vs State-of-the-Art Models: A Benchmarking Study in Keyphrase Generation Taskcited by 12
  27. 2023Continually Improving Extractive QA via Human Feedbackcited by 11
  28. 2024PAFT: A Parallel Training Paradigm for Effective LLM Fine-Tuningcited by 11
  29. 2024Fine-Grained Reward Optimization for Machine Translation using Error Severity Mappingscited by 11
  30. 2023Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challengescited by 10
  31. 2023Let Me Teach You: Pedagogical Foundations of Feedback for Language Modelscited by 9
  32. 2024Multimodal Query Suggestion with Multi-Agent Reinforcement Learning from Human Feedbackcited by 9
  33. 2024Measuring the Influence of Incorrect Code on Test Generationcited by 9
  34. 2024Modeling User Preferences with Automatic Metrics: Creating a High-Quality Preference Dataset for Machine Translationcited by 8
  35. 2023FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human Feedbackcited by 7
  36. 2024It Takes Two: On the Seamlessness between Reward and Policy Model in RLHFcited by 5
  37. 2022Federated Learning with Noisy User Feedbackcited by 4
  38. 2023Kernelized Offline Contextual Dueling Banditscited by 4

50 most cited of 71 All 71 (JSON)