SOURCE-LINKED INTELLIGENCE

Quit While You're Ahead: Quit for Efficient Candidate Generation in Machine Translation Reranking

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Reranking methods, such as Minimum Bayes Risk (MBR) decoding and Quality Estimation (QE) reranking, have been widely used in modern neural machine translation (NMT) to select an output from a set of candidate hypotheses. However, the performance gains come at the cost of high inference latency. Existing acceleration methods target MBR decoding and reduce only the reranking computation, leaving QE reranking unaddressed and candidate generation---which can be the larger computational bottleneck---largely untouched. In this work, we propose Quit (Quantifying Uncertainty for Incremental Terminatio

Read original source ↗ Open in workspace

recordType

paper

region

Global