AI ethics evidence index Search
Source-linked daily record
Evidence record 3195 · automatically gathered

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

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 recove

Record details

Published: 2 June 2026
Source: arXiv
Category: Research
Topics: Regulation · Safety & alignment
Retrieved: 14 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Shared topic: Regulation · Shared topic: Safety & alignment

CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference Alignment

arXiv · 13 June 2026

Shared topic: Regulation · Shared topic: Safety & alignment

Geopolitical alignment: Endorsement effects in large language models

arXiv · 10 July 2026

Shared topic: Regulation · Shared topic: Safety & alignment

Faithful or evasive? An empirical study on translation norm preferences of Chinese and American LLMs in Chinese official political and policy discourse

Frontiers in Artificial Intelligence · 10 August 2026

Shared topic: Regulation · Shared topic: Safety & alignment

Detection Is Cheap, Routing Is Learned: Why Refusal-Based Alignment Evaluation Fails

arXiv · 18 March 2026

Shared topic: Regulation · Shared topic: Safety & alignment

China works on AI safety benchmark as regulators target large model risks

SCMP Tech (HK/CN) · 13 July 2026

Shared topic: Regulation · Shared topic: Safety & alignment

Huawei’s Ren Zhengfei backs Tau Scaling Law to beat US sanctions

SCMP Tech (HK/CN) · 24 July 2026

How to cite this record

ethics.ai (2 June 2026), “AlignAtt4LLM: Fast AlignAtt for Decoder-Only LLMs at IWSLT 2026 Simultaneous Speech Translation Task,” evidence record 3195, https://ethics.ai/record/3195 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.