# On the Hallucination in Simultaneous Machine Translation

arXiv: https://arxiv.org/abs/2406.07239 · HTML: https://mlsanity.com/paper/2406.07239/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 11 Jun 2024.

## Builds on (most cited first, 23 of 23)

- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks](https://mlsanity.com/paper/1506.03099/) (2015)
- [Word Alignment by Fine-tuning Embeddings on Parallel Corpora](https://mlsanity.com/paper/2101.08231/) (2021)
- [On Hallucination and Predictive Uncertainty in Conditional Language Generation](https://mlsanity.com/paper/2103.15025/) (2021)
- [The Curious Case of Hallucinations in Neural Machine Translation](https://mlsanity.com/paper/2104.06683/) (2021)
- [On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation](https://mlsanity.com/paper/2005.03642/) (2020)
- [Bridging the Gap between Training and Inference for Neural Machine Translation](https://mlsanity.com/paper/1906.02448/) (2019)
- [Monotonic Multihead Attention](https://mlsanity.com/paper/1909.12406/) (2019)
- [Analyzing the Source and Target Contributions to Predictions in Neural Machine Translation](https://mlsanity.com/paper/2010.10907/) (2020)
- [Domain Robustness in Neural Machine Translation](https://mlsanity.com/paper/1911.03109/) (2019)
- [Efficient Wait-k Models for Simultaneous Machine Translation](https://mlsanity.com/paper/2005.08595/) (2020)
- [Measuring and Increasing Context Usage in Context-Aware Machine Translation](https://mlsanity.com/paper/2105.03482/) (2021)
- [Simultaneous Translation Policies: From Fixed to Adaptive](https://mlsanity.com/paper/2004.13169/) (2020)
- [Information-Transport-based Policy for Simultaneous Translation](https://mlsanity.com/paper/2210.12357/) (2022)
- [Prevent the Language Model from being Overconfident in Neural Machine Translation](https://mlsanity.com/paper/2105.11098/) (2021)
- [Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policy](https://mlsanity.com/paper/2109.05238/) (2021)
- [Modeling Dual Read/Write Paths for Simultaneous Machine Translation](https://mlsanity.com/paper/2203.09163/) (2022)
- [Improving Simultaneous Translation by Incorporating Pseudo-References with Fewer Reorderings](https://mlsanity.com/paper/2010.11247/) (2020)
- [Reducing Position Bias in Simultaneous Machine Translation with Length-Aware Framework](https://mlsanity.com/paper/2203.09053/) (2022)
- [Turning Fixed to Adaptive: Integrating Post-Evaluation into Simultaneous Machine Translation](https://mlsanity.com/paper/2210.11900/) (2022)
- [Improving Simultaneous Machine Translation with Monolingual Data](https://mlsanity.com/paper/2212.01188/) (2022)
- [Probing Causes of Hallucinations in Neural Machine Translations](https://mlsanity.com/paper/2206.12529/) (2022)
- [CBSiMT: Mitigating Hallucination in Simultaneous Machine Translation with Weighted Prefix-to-Prefix Training](https://mlsanity.com/paper/2311.03672/) (2023)

## Built on by (most cited first, 1 of 1)

- [The Rise of Darkness: Safety-Utility Trade-Offs in Role-Playing Dialogue Agents](https://mlsanity.com/paper/2502.20757/) (2025)

## Abstract (arXiv)

It is widely known that hallucination is a critical issue in Simultaneous Machine Translation (SiMT) due to the absence of source-side information. While many efforts have been made to enhance performance for SiMT, few of them attempt to understand and analyze hallucination in SiMT. Therefore, we conduct a comprehensive analysis of hallucination in SiMT from two perspectives: understanding the distribution of hallucination words and the target-side context usage of them. Intensive experiments demonstrate some valuable findings and particularly show that it is possible to alleviate hallucination by decreasing the over usage of target-side information for SiMT.