ExPosST: Explicit Positioning with Adaptive Masking for LLM-Based Simultaneous Machine Translation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918413931118592 |
|---|---|
| author | Shang, Yuzhe Gao, Pengzhi Yang, Yazheng Ma, Jiayao Liu, Wei Luan, Jian Su, Jinsong |
| author_facet | Shang, Yuzhe Gao, Pengzhi Yang, Yazheng Ma, Jiayao Liu, Wei Luan, Jian Su, Jinsong |
| contents | Large language models (LLMs) have recently demonstrated promising performance in simultaneous machine translation (SimulMT). However, applying decoder-only LLMs to SimulMT introduces a positional mismatch, which leads to a dilemma between decoding efficiency and positional consistency. Existing approaches often rely on specific positional encodings or carefully designed prompting schemes, and thus fail to simultaneously achieve inference efficiency, positional consistency, and broad model compatibility. In this work, we propose ExPosST, a general framework that resolves this dilemma through explicit position allocation. ExPosST reserves fixed positional slots for incoming source tokens, enabling efficient decoding with KV cache across different positional encoding methods. To further bridge the gap between fine-tuning and inference, we introduce a policy-consistent fine-tuning strategy that aligns training with inference-time decoding behavior. Experiments across multiple language pairs demonstrate that ExPosST effectively supports simultaneous translation under diverse policies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_14903 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ExPosST: Explicit Positioning with Adaptive Masking for LLM-Based Simultaneous Machine Translation Shang, Yuzhe Gao, Pengzhi Yang, Yazheng Ma, Jiayao Liu, Wei Luan, Jian Su, Jinsong Computation and Language Large language models (LLMs) have recently demonstrated promising performance in simultaneous machine translation (SimulMT). However, applying decoder-only LLMs to SimulMT introduces a positional mismatch, which leads to a dilemma between decoding efficiency and positional consistency. Existing approaches often rely on specific positional encodings or carefully designed prompting schemes, and thus fail to simultaneously achieve inference efficiency, positional consistency, and broad model compatibility. In this work, we propose ExPosST, a general framework that resolves this dilemma through explicit position allocation. ExPosST reserves fixed positional slots for incoming source tokens, enabling efficient decoding with KV cache across different positional encoding methods. To further bridge the gap between fine-tuning and inference, we introduce a policy-consistent fine-tuning strategy that aligns training with inference-time decoding behavior. Experiments across multiple language pairs demonstrate that ExPosST effectively supports simultaneous translation under diverse policies. |
| title | ExPosST: Explicit Positioning with Adaptive Masking for LLM-Based Simultaneous Machine Translation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2603.14903 |