Author

Shan-Bo Cheng

h-index 5 View on Semantic Scholar

We have 1 of 7 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Feb 2026

GRRM: Group Relative Reward Modeling for Machine Translation

Empirical evaluations confirm that GRRM achieves competitive ranking accuracy among all baselines; integrating GRRM into the GRPO training not only improves general translation quality but also unlocks reasoning capabilities comparable to state-of-the-art reasoning models.

Sen Yang, Shan-Bo Cheng, Lu Xu et al. · arXiv.org · 1 citation