ReflectMT internalizes reflection via two-stage RL to enable direct high-quality machine translation that outperforms explicit reasoning models like DeepSeek-R1 on WMT24 while using 94% fewer tokens.
Mt-r1-zero: Advancing llm-based machine translation via r1-zero-like reinforcement learning
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
UniR is a composable reasoning module trained with verifiable rewards and added to frozen LLMs via logit summation, enabling modular composition and weak-to-strong generalization across tasks and model sizes.
RL-trained lightweight controller using answer statistics improves trade-offs among correctness, latency, and total samples in adaptive sampling for LLM test-time scaling.
citing papers explorer
-
ReflectMT: Internalizing Reflection for Efficient and High-Quality Machine Translation
ReflectMT internalizes reflection via two-stage RL to enable direct high-quality machine translation that outperforms explicit reasoning models like DeepSeek-R1 on WMT24 while using 94% fewer tokens.
-
Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling
RL-trained lightweight controller using answer statistics improves trade-offs among correctness, latency, and total samples in adaptive sampling for LLM test-time scaling.