让翻译模型学会动态等待，提前输出更准，延迟更低。
Dynamic Lagging for Simultaneous Translation
- 用稳定前缀微调大模型，让其能感知源文本进度并决定何时输出。
- 在多个测试集上提升早期输出质量，降低校准误差，效果优于传统延迟控制方法。
- 无需额外训练，仅靠信心阈值即可实现流畅翻译，适合实时系统部署。
在级联式同时语音翻译中，机器翻译系统无法控制上游识别器的读写节奏：必须从不断增长的源文本前缀中判断应输出多少目标文本。本文通过在稳定前缀（即任何部分源文本与模型完整输出共享的最长前缀）和完整句对上微调基于Qwen3-8B的解码器模型，使其具备前缀感知能力。通过单次强制解码轮次，将已承诺的目标文本随新源输入持续传递，从根本上消除闪烁问题。该方法在英译德、日、中任务中模拟源流，保持全句翻译质量的同时显著提升最差位置分块质量，并改善词级提交置信度的校准性，使早期源前缀的期望校准误差（ECE）低于稳定前缀基准。仅使用一个训练免调阈值，其表现优于三种延迟控制机制中的任意一种，在FLEURS、WMT24++和CoVoST~2测试集上，无论使用COMET还是MetricX指标均表现更优。
原文摘要 · Abstract (English)
In cascaded simultaneous speech translation, the machine translation (MT) system cannot control the read--write schedule of the upstream recognizer: it must decide, from a growing source prefix, how much target text to commit. We make a sentence-trained, decoder-only LLM prefix-aware by fine-tuning it on stable prefixes---the longest prefix that any translation up to the current partial source has shared with the model's own full-source output---mixed with full-sentence pairs, and prompt it through a single force-decode turn that carries the committed target forward as more source arrives, making the system flicker-free by construction. We fine-tune Qwen3-8B for EN to DE, JA, ZH, simulating the source stream with reference-transcript prefixes. Prefix finetuning preserves full-sentence quality while improving worst-position chunk quality, and it improves calibration of token-level commit confidence, reducing expected calibration error (ECE) on early source prefixes against a stable-prefix oracle. A single training-free threshold on that confidence is the most effective of the three latency controls we compare: it traces a continuous quality--latency frontier that outperforms the discrete wait-$k$ and target-suffix-deletion quality-latency tradeoff mechanisms. The effect holds well on FLEURS, WMT24++, and CoVoST~2 test sets, under both COMET and MetricX.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。