mlsanityData to 7 Oct 2026

Wat zei je? Detecting Out-of-Distribution Translations with Variational Transformers

arXiv 2006.08344 ↗First posted 8 Jun 2020cs.CL cs.LG stat.MLcited by 31

Not on the map. Why?

Abstract (arXiv)

We detect out-of-training-distribution sentences in Neural Machine Translation using the Bayesian Deep Learning equivalent of Transformer models. For this we develop a new measure of uncertainty designed specifically for long sequences of discrete random variables -- i.e. words in the output sentence. Our new measure of uncertainty solves a major intractability in the naive application of existing approaches on long sentences. We use our new measure on a Transformer model trained with dropout approximate inference. On the task of German-English translation using WMT13 and Europarl, we show that with dropout uncertainty our measure is able to identify when Dutch source sentences, sentences which use the same word types as German, are given to the model instead of German.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 6; 2023: 5; 2024: 6; 2025: 4; 2026: 6.

31 papers.

Sort:

By area:

  1. 2022Out-of-Distribution Detection and Selective Generation for Conditional Language Modelscited by 193
  2. 2024Language Model Cascades: Token-level uncertainty and beyondcited by 115
  3. 2024Calibrating Large Language Models Using Their Generations Onlycited by 63
  4. 2023Uncertainty in Natural Language Generation: From Theory to Applicationscited by 61
  5. 2024MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMscited by 45
  6. 2023Uncertainty in Natural Language Processing: Sources, Quantification, and Applicationscited by 44
  7. 2022Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcitycited by 24
  8. 2022Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Datacited by 21
  9. 2024Non-Exchangeable Conformal Language Generation with Nearest Neighborscited by 21
  10. 2021Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Trainingcited by 19
  11. 2024Embedding Trajectory for Out-of-Distribution Detection in Mathematical Reasoningcited by 18
  12. 2022Out of Distribution Data Detection Using Dropout Bayesian Neural Networkscited by 15
19 more
  1. 2021Should We Trust This Summary? Bayesian Abstractive Summarization to The Rescuecited by 11
  2. 2024Your Finetuned Large Language Model is Already a Powerful Out-of-distribution Detectorcited by 11
  3. 2021Trust It or Not: Confidence-Guided Automatic Radiology Report Generationcited by 9
  4. 2023Active Learning for Abstractive Text Summarizationcited by 6
  5. 2021Bayesian Active Summarizationcited by 5
  6. 2022Combining Data Generation and Active Learning for Low-Resource Question Answeringcited by 5
  7. 2025aiXamine: Simplified LLM Safety and Securitycited by 4
  8. 2025Improving the Calibration of Confidence Scores in Text Generation Using the Output Distribution's Characteristicscited by 4
  9. 2026Semantic Uncertainty Quantification of Hallucinations in LLMs: A Quantum Tensor Network Based Methodcited by 4
  10. 2023Active Learning for Natural Language Generationcited by 3
  11. 2022Learning Confidence for Transformer-based Neural Machine Translationcited by 2
  12. 2025Enhancing RAG with Active Learning on Conversation Records: Reject Incapables and Answer Capablescited by 2
  13. 2023DA3: A Distribution-Aware Adversarial Attack against Language Modelscited by 1
  14. 2026AP-OOD: Attention Pooling for Out-of-Distribution Detectioncited by 1
  15. 2026Variational Neurons in Transformers for Language Modelingcited by 1
  16. 2025ATGen: A Framework for Active Text Generationcited by 0
  17. 2026ESG-Bench: Benchmarking Long-Context ESG Reports for Hallucination Mitigationcited by 0
  18. 2026Confident in a Confidence Score: Investigating the Sensitivity of Confidence Scores to Supervised Fine-Tuningcited by 0
  19. 2026Loss-Based Active Learning for Neural Abstractive Summarizationcited by 0