AlignAtt4LLM: Fast AlignAtt for Decoder-Only LLMs at IWSLT 2026 Simultaneous Speech Translation Task

Quentin Fuxa, Dominik Macháček


Abstract
We describe AlignAtt4LLM, an IWSLT 2026 simultaneous speech translation system for English to German, Italian, and Chinese. The system is a synchronous cascade: Qwen3-ASR with forced alignment produces an incrementally updated source transcript, and Gemma-4 E4B-it translates that prefix under an MT-side AlignAtt policy. To our knowledge, this is the first application of AlignAtt to a decoder-only LLM, where the encoder-decoder cross-attention used by earlier AlignAtt systems is absent. We recover a usable policy by proposing (1) an explicit source span in the prompt, (2) offline selection of translation-specific alignment heads, (3) selective qk-fast replay of the draft-to-source attention block, and (4) runtime query/key capture that preserves model outputs bit-identically. On the IWSLT 2026 development set, AlignAtt4LLM outperforms the supplied baselines for the European target languages, English to German and English to Italian, in both the low-latency regime around 2 seconds and the high-latency regime below 4 seconds CU-LongYAAL. Results for English to Chinese are more mixed, but the method is not tied to Gemma-4: because AlignAtt4LLM only requires a deterministic prompt layout, calibrated attention heads, and query/key capture, the same policy can be reapplied to stronger translation-focused decoder-only MT backbones for non-European target languages.
Anthology ID:
2026.iwslt-1.32
Volume:
Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026)
Month:
July
Year:
2026
Address:
San Diego, USA (in-person and online)
Editors:
Elizabeth Salesky, Antonios Anastasopoulos, Matteo Negri, Marcello Federico
Venues:
IWSLT | WS
SIG:
SIGSLT
Publisher:
Association for Computational Linguistics
Note:
Pages:
284–295
Language:
URL:
https://aclanthology.org/2026.iwslt-1.32/
DOI:
Bibkey:
Cite (ACL):
Quentin Fuxa and Dominik Macháček. 2026. AlignAtt4LLM: Fast AlignAtt for Decoder-Only LLMs at IWSLT 2026 Simultaneous Speech Translation Task. In Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026), pages 284–295, San Diego, USA (in-person and online). Association for Computational Linguistics.
Cite (Informal):
AlignAtt4LLM: Fast AlignAtt for Decoder-Only LLMs at IWSLT 2026 Simultaneous Speech Translation Task (Fuxa & Macháček, IWSLT 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.iwslt-1.32.pdf