# Decoder-only Streaming Transformer for Simultaneous Translation arXiv: https://arxiv.org/abs/2406.03878 ยท HTML: https://mlsanity.com/paper/2406.03878/ ## Key facts - Cited by 11 papers in the map (data through 14 Oct 2026). - Builds on 28 of its 47 references that are in the map. - First posted on arXiv 6 Jun 2024. ## Builds on (most cited first, 28 of 28) - [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023) - [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015) - [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018) - [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019) - [Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/1711.02281/) (2017) - [Learning to Translate in Real-time with Neural Machine Translation](https://mlsanity.com/paper/1610.00388/) (2016) - [Monotonic Multihead Attention](https://mlsanity.com/paper/1909.12406/) (2019) - [SimulMT to SimulST: Adapting Simultaneous Text Translation to End-to-End Simultaneous Speech Translation](https://mlsanity.com/paper/2011.02048/) (2020) - [Efficient Wait-k Models for Simultaneous Machine Translation](https://mlsanity.com/paper/2005.08595/) (2020) - [Incremental Decoding and Training Methods for Simultaneous Translation in Neural Machine Translation](https://mlsanity.com/paper/1806.03661/) (2018) - [Decoder-Only or Encoder-Decoder? Interpreting Language Model as a Regularized Encoder-Decoder](https://mlsanity.com/paper/2304.04052/) (2023) - [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) - [Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policy](https://mlsanity.com/paper/2109.05238/) (2021) - [Hidden Markov Transformer for Simultaneous Machine Translation](https://mlsanity.com/paper/2303.00257/) (2023) - [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) - [Gaussian Multi-head Attention for Simultaneous Machine Translation](https://mlsanity.com/paper/2203.09072/) (2022) - [Reducing Position Bias in Simultaneous Machine Translation with Length-Aware Framework](https://mlsanity.com/paper/2203.09053/) (2022) - [Wait-info Policy: Balancing Source and Target at Information Level for Simultaneous Machine Translation](https://mlsanity.com/paper/2210.11220/) (2022) - [Learning Optimal Policy for Simultaneous Machine Translation via Binary Search](https://mlsanity.com/paper/2305.12774/) (2023) - [Turning Fixed to Adaptive: Integrating Post-Evaluation into Simultaneous Machine Translation](https://mlsanity.com/paper/2210.11900/) (2022) - [On the Sub-Layer Functionalities of Transformer Decoder](https://mlsanity.com/paper/2010.02648/) (2020) - [Non-autoregressive Streaming Transformer for Simultaneous Translation](https://mlsanity.com/paper/2310.14883/) (2023) - [Glancing Future for Simultaneous Machine Translation](https://mlsanity.com/paper/2309.06179/) (2023) - [Simultaneous Machine Translation with Tailored Reference](https://mlsanity.com/paper/2310.13588/) (2023) - [Adaptive Policy with Wait-k Model for Simultaneous Translation](https://mlsanity.com/paper/2310.14853/) (2023) - [Unified Segment-to-Segment Framework for Simultaneous Sequence Generation](https://mlsanity.com/paper/2310.17940/) (2023) ## Built on by (most cited first, 11 of 11) - [Streaming Sequence-to-Sequence Learning with Delayed Streams Modeling](https://mlsanity.com/paper/2509.08753/) (2025) - [StreamingThinker: Large Language Models Can Think While Reading](https://mlsanity.com/paper/2510.17238/) (2025) - [SeqPO-SiMT: Sequential Policy Optimization for Simultaneous Machine Translation](https://mlsanity.com/paper/2505.20622/) (2025) - [LLM as Effective Streaming Processor: Bridging Streaming-Batch Mismatches with Group Position Encoding](https://mlsanity.com/paper/2505.16983/) (2025) - [Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation](https://mlsanity.com/paper/2501.00868/) (2025) - [LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offline](https://mlsanity.com/paper/2504.09570/) (2025) - [From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models](https://mlsanity.com/paper/2603.04592/) (2026) - [Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies](https://mlsanity.com/paper/2601.11002/) (2026) - [Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies](https://mlsanity.com/paper/2509.21801/) (2025) - [AdaSR: Adaptive Streaming Reasoning with Hierarchical Relative Policy Optimization](https://mlsanity.com/paper/2606.14694/) (2026) - [Dual-Stream Simultaneous Translation via 2D Grid Attention](https://mlsanity.com/paper/2609.34902/) (2026) ## Abstract (arXiv) Simultaneous Machine Translation (SiMT) generates translation while reading source tokens, essentially producing the target prefix based on the source prefix. To achieve good performance, it leverages the relationship between source and target prefixes to exact a policy to guide the generation of translations. Although existing SiMT methods primarily focus on the Encoder-Decoder architecture, we explore the potential of Decoder-only architecture, owing to its superior performance in various tasks and its inherent compatibility with SiMT. However, directly applying the Decoder-only architecture to SiMT poses challenges in terms of training and inference. To alleviate the above problems, we propose the first Decoder-only SiMT model, named Decoder-only Streaming Transformer (DST). Specifically, DST separately encodes the positions of the source and target prefixes, ensuring that the position of the target prefix remains unaffected by the expansion of the source prefix. Furthermore, we propose a Streaming Self-Attention (SSA) mechanism tailored for the Decoder-only architecture. It is capable of obtaining translation policy by assessing the sufficiency of input source information and integrating with the soft-attention mechanism to generate translations. Experiments demonstrate that our approach achieves state-of-the-art performance on three translation tasks.