2 papers
cs.CL2026
HOMURA: Taming the Sand-Glass for Time-Constrained LLM Translation via Reinforcement Learning
Ziang Cui, Mengran Yu, Tianjiao Li +4
Large Language Models (LLMs) have achieved remarkable strides in multilingual translation but are hindered by a systemic cross-lingual verbosity bias, rendering them unsuitable for…
cs.CL2025
RIVAL: Reinforcement Learning with Iterative and Adversarial Optimization for Machine Translation
Tianjiao Li, Mengran Yu, Chenyu Shi +6
Large language models (LLMs) possess strong multilingual capabilities, and combining Reinforcement Learning from Human Feedback (RLHF) with translation tasks has shown great potent…