
TL
Tianyuan Li, Xihan Yang, Chenglong Wang, Yuzhang Wu, Jingbo Zhu, Tong Xiao
· 1 min read
ResearcharXiv cs.CL
TRAC: Efficient Diffusion Language Models for Machine Translation via Length-Aware Decoding
arXiv:2611.25643v1 Announce Type: new
Abstract: Machine translation with large language models requires both high translation quality and low generation latency. Accelerating translation while preserving quality is therefore essential for practical deployment. Diffusion large language models (dLLMs) can generate tokens at arbitrary target positions through iterative denoising, offering a new paradigm for parallel translation beyond sequential autoregressive decoding. However, existing methods still incur redundant computation: fixed target generation lengths waste computation on unused positions, while confidence-only commitment delays medium-confidence tokens whose predictions have largely stabilized. To address these issues, we propose TRAC, a training-free adaptive decoding method for diffusion machine translation. TRAC adapts the target generation length using source length and translation direction, with a conservative fallback to the maximum length for empty or unusually short outputs. It preserves high-confidence commitment while identifying temporally stable medium-confidence tokens for early commitment using cross-step top-1 persistence and approximate Jensen-Shannon divergence over Top-$K$ distributions. On bidirectional Chinese-English translation across FLORES-200, WMT23, and NTREX-128, TRAC reduces model forward calls by 24.9% to 36.8% and achieves sentence-level generation speedups of 1.91 to 2.19 times over Fast-dLLM, with only a 0.02-point decrease in macro-average COMET. These results demonstrate that adaptive generation lengths and stability-aware token commitment improve the efficiency of diffusion machine translation.
Original source
This story was published by arXiv cs.CL and written by Tianyuan Li, Xihan Yang, Chenglong Wang, Yuzhang Wu, Jingbo Zhu, Tong Xiao. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


