The DOI matches its Crossref record; 33 of the 36 references it cites were found in a registry or an index.
On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation
Open accessAbstract
The standard training algorithm in neural machine translation (NMT) suffers from exposure bias, and alternative algorithms have been proposed to mitigate this.However, the practical impact of exposure bias is under debate.In this paper, we link exposure bias to another well-known problem in NMT, namely the tendency to generate hallucinations under domain shift.In experiments on three datasets with multiple test domains, we show that exposure bias is partially to blame for hallucinations, and that training with Minimum Risk Training, which avoids exposure bias, can mitigate this.Our analysis explains why exposure bias is more problematic under domain shift, and also links exposure bias to the beam search problem, i.e. performance deterioration with increasing beam size.Our results provide a new justification for methods that reduce exposure bias: even if they do not increase performance on in-domain test sets, they can increase model robustness to domain shift.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Further, in longform tasks consisting of generating multiple sentences or paragraphs, the hallucination problem can be exacerbated due to the issue of exposure bias (Wang & Sennrich, 2020).”
From Chain-of-Verification Reduces Hallucination in Large Language Models (2023) · cites this paper as Wang & Sennrich, 2020
In the citing paper
“Durmus et al. (2020) and Wang et al. (2020) suggested using QG and QA to identify factual inconsistencies in abstractive summaries, which is more Precisionoriented.”
From Q2: : Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering (2021) · cites this paper as Wang et al. (2020)
In the citing paper
“Their approach is based on the intuition that if a summary is consistent with its source, questions asked on the summary and the source should result in similar answers.”
From Q2: : Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering (2021) · cites this paper as Wang et al. (2020)
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
Rethinking the Inception Architecture for Computer Vision
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.308 · Cited by 32,138
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766
Neural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213
Convolutional Sequence to Sequence Learning
Gehring, J., Auli, M., Grangier, D., Yarats, D., & Dauphin, Y. N. (2017) · arXiv · doi:10.48550/arxiv.1705.03122 · Cited by 2,850
Minimum error rate training in statistical machine translation
Och, F. J. (2003) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.3115/1075096.1075117 · Cited by 2,728
A Call for Clarity in Reporting BLEU Scores
Post, M. (2018) · Proceedings of the Third Conference on Machine Translation: Research Papers · doi:10.18653/v1/w18-6319 · Cited by 2,112
Assessing Agreement on Classification Tasks: The Kappa Statistic
Carletta, J. (1996) · arXiv · doi:10.48550/arxiv.cmp-lg/9602004 · Cited by 2,088
Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
Bengio, S., Vinyals, O., Jaitly, N., & Shazeer, N. (2015) · arXiv · doi:10.48550/arxiv.1506.03099 · Cited by 1,621
Flagged first, then by citations
3 of the 36 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Items 101–132 of 132
Improving Faithfulness in Thai Abstractive Text Summarization using Highlight-Aware Copy Pretraining
Porkaew, P., Jumpathong, S., Luantangsrisuk, V., Phrombut, C., Phaholphinyo, S., Kosawat, K., Boonkwan, P., & Supnithi, T. (2024) · International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP) · doi:10.1109/isai-nlp64410.2024.10799333 · Cited by 1
Pan, W., Han, B., & Jiang, P. (2025) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2025.1482327 · Cited by 1
Improving Scheduled Sampling with Elastic Weight Consolidation for Neural Machine Translation
Korakakis, M., & Vlachos, A. (2022) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2022.findings-emnlp.536 · Cited by 2
Improving Neural Machine Translation with Offline Evaluations
Park, M.-K., & Lee, B.-J. (2023) · International Joint Conference on Natural Language Processing and Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL) · doi:10.18653/v1/2023.ijcnlp-main.25 · Cited by 1
Sequence-level Large Language Model Training with Contrastive Preference Optimization
Feng, Z., Ram, D., Hawkins, C., Rawal, A., Zhao, J., & Zha, S. (2025) · Findings of the Association for Computational Linguistics: NAACL · doi:10.18653/v1/2025.findings-naacl.233 · Cited by 2
Hallucinations in Abstractive Text Summarization with Large Language Models
Delpisheh, N., & Chali, Y. (2025) · International Generative AI and Computational Language Modelling Conference (GACLM) · doi:10.1109/gaclm67198.2025.11231924 · Cited by 1
Acceptance-Guided Adaptive Speculative Decoding for Efficient Large Language Model Inference
Sun, W., Zhu, Z. G., Dai, Y., Guo, B., Sun, Y., & Zhou, F. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463423 · Cited by 1
Hallucinations in LLMs: a lifecycle-based survey of causes, detection, mitigation, and prevention
Lamba, N., Tiwari, S., & Gaur, M. (2026) · International Journal of Data Science and Analytics · doi:10.1007/s41060-026-01214-6 · Cited by 1
Sun, S., Huang, Y., Zhao, D., Yu, Y., & Meng, J. (2023) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-023-01856-z · Cited by 1
Guo, B., Feng, C., Liu, F., Li, X., & Wang, X. (2023) · Communications in computer and information science · doi:10.1007/978-981-99-7894-6_11 · Cited by 1
Hallucination Detection for Grounded Instruction Generation
Zhao, L., Nguyen, K., & Daumé, H. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.266 · Cited by 2
Le, D. A., Bui, A. M. T., Nguyen, P. T., & Ruscio, D. D. (2024) · Proceedings of the ... ACM-IEEE International Symposium on Empirical Software Engineering and Measurement/International Symposium on Empirical Software Engineering and Measurement · doi:10.1145/3674805.3686682 · Cited by 1
The Highs and Lows of Simple Lexical Domain Adaptation Approaches for Neural Machine Translation
Bogoychev, N., & Chen, P. (2021) · Workshop on Insights from Negative Results in NLP (Insights) · doi:10.18653/v1/2021.insights-1.12 · Cited by 1
Methods for Estimating and Improving Robustness of Language Models
Štefánik, M. (2022) · Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop (NAACL SRW) · doi:10.18653/v1/2022.naacl-srw.6 · Cited by 1
Soft Alignment Objectives for Robust Adaptation of Language Generation
Štefánik, M., Kadlčík, M., & Sojka, P. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.492 · Cited by 1
Evaluating Parameter Efficient Learning for Generation
Xu, P., Patwary, M. A., Prabhumoye, S., Adams, V., Prenger, R., Ping, W., Lee, N., Shoeybi, M., & Catanzaro, B. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.319 · Cited by 1
Quality Scoring of Source Words in Neural Translation Models
Jain, P., Sarawagi, S., & Tomar, T. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.732 · Cited by 1
Fixing exposure bias with imitation learning needs powerful oraclesPreprint
Hormann, L., & Sokolov, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.04114 · Cited by 1
Masked Adversarial Generation for Neural Machine TranslationPreprint
Idrissi, B. Y., & Clinchant, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.00417 · Cited by 1
Elastic Weight Removal for Faithful and Abstractive Dialogue Generation
Daheim, N., Dziri, N., Sachan, M., Gurevych, I., & Ponti, E. M. (2023) · arXiv · doi:10.48550/arxiv.2303.17574
Korakakis, M., & Vlachos, A. (2021) · arXiv (Cornell University)
Hubert, R., Sokolov, A., & Riezler, S. (2023) · International Conference on Spoken Language Translation (IWSLT) · doi:10.18653/v1/2023.iwslt-1.4
Wang, C., Liu, Y., & Lam, W. P. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.601 · Cited by 2
Self-citationTreeSwap: Data Augmentation for Machine Translation via Dependency Subtree Swapping
Nagy, A., Lakatos, D., Barta, B., & Ács, J. (2023) · International conference Recent advances in natural language processing · doi:10.26615/978-954-452-092-2_082
Elewa, M. S. A. H., Hamdi, A., Kassab, H., & Shaban, K. (2025) · IEEE/ACS International Conference on Computer Systems and Applications (AICCSA) · doi:10.1109/aiccsa66935.2025.11315358 · Cited by 2
Neural posterior estimation with autoregressive tiling for detecting objects in astronomical images
Regier, J. (2026) · The Annals of Applied Statistics · doi:10.1214/25-aoas2125
Contributions to evaluating and improving the faithfulness for text generation
Zhang, K. (2025) · theses.fr (ABES) · doi:10.70675/28453a20z78f2z4fa2za6edz700065e69e97
Adversarial Abductive Dialogue Framework with Reinforcement for Tackling LLM Hallucination
Galitsky, B. (2026) · Springer eBooks · doi:10.1007/978-3-032-16524-4_3
LLM-Assisted Multi-domain Translation with Composed In-Domain Experts
Shi, X., Zhou, A., Chen, Y., Huang, K., Han, W., & Xu, J. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-0199-0_5
Zhao, K., Hou, J., Zhang, L. H., Wu, Z., Li, Q., & Wei, S. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582040
Retrieval for User-Centered Translation: Lessons from RAG-based Tools for Low-Resource Domains
Merx, R., & Vylomova, E. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3808535
An Investigation of Hallucination Phenomena in Indian Low-Resource Language
Baghel, P., Yadav, R., & Kumar, N. (2026) · International Conference on Secure Cyber Computing and Communications (ICSCCC) · doi:10.1109/icsccc69031.2026.11600243
Metadata
- Authors
- Wang, C., & Sennrich, R.
- Affiliations
- University of Edinburgh (GB)
- University of Zurich (CH)
- Corresponding author
- Sennrich, Rico
- Venue
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Published
- 2020
- Pages
- 3544-3552
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W3035214886
- Cited by
- 118
- References
- 36
- Citations by year
- 2026: 7 · 2025: 14 · 2024: 11 · 2023: 31 · 2022: 22 · 2021: 28 · 2020: 5
- FWCI
- 8.21
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- Edinburgh Research Explorer (University of Edinburgh) (submittedVersion, cc-by)
- Zurich Open Repository and Archive (University of Zurich) (submittedVersion, cc-by)
- Funders
- National Science Foundation
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung (176727)
- Samsung
- Engineering and Physical Sciences Research Council (EP/S001271/1)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Keywords
- exposure bias, hallucinations, domain shift, neural machine translation, beam search, spot size, model robustness, training algorithms
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
