作者位次 #3/4ACL 2026Findings· Findings of ACL
Mending the Holes: Mitigating Reward Hacking in Reinforcement Learning for Multilingual Translation
Yifeng Liu · Siqi Ouyang · Yatish H R · Lei Li
摘要
Large Language Models (LLMs) have demonstrated remarkable capability in machine translation on high-resource language pairs, yet their performance on low-resource translation still lags behind. Existing post-training methods rely heavily on high-quality parallel data, which are often scarce or un...