SOURCE-LINKED INTELLIGENCE

Generating Adversarial Texts for Machine Translation via GRPO

arXiv · AI, language, vision and robotics · article · Sep 5, 2026 · UTC

As machine translation (MT) systems continue to improve, standard benchmarks become less informative for exposing remaining weaknesses. Traditional methods for creating challenging test sets rely on expensive manual creation or curation, while automated approaches struggle to produce sets with the necessary translation difficulty and linguistic diversity. We propose a scalable reinforcement-learning-based approach for rewriting existing source texts into instances that are more difficult to translate for MT systems. We fine-tune a large language model with Group Relative Policy Optimization (G

Read original source ↗ Open in workspace

recordType

paper

region

Global