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.
Title resolution pending
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6representative citing papers
MORPHOGEN is a new multilingual benchmark for testing LLMs on gender-aware morphological generation via rewriting first-person sentences to the opposite gender in French, Arabic, and Hindi.
Multilingual pretraining develops translation in two phases: early copying driven by surface similarities, followed by generalizing mechanisms while copying is refined.
COMPASS uses semantic clustering on multilingual embeddings to select auxiliary data for PEFT adapters, outperforming linguistic-similarity baselines on multilingual benchmarks while supporting continual adaptation.
A language-adaptive combination of generalist, specialist, and ensemble transformer models achieves 0.796 macro F1 and 0.826 accuracy on multilingual polarization detection across 22 languages.
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.
-
MORPHOGEN: A Multilingual Benchmark for Evaluating Gender-Aware Morphological Generation
MORPHOGEN is a new multilingual benchmark for testing LLMs on gender-aware morphological generation via rewriting first-person sentences to the opposite gender in French, Arabic, and Hindi.
-
Copy First, Translate Later: Interpreting Translation Dynamics in Multilingual Pretraining
Multilingual pretraining develops translation in two phases: early copying driven by surface similarities, followed by generalizing mechanisms while copying is refined.
-
COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling
COMPASS uses semantic clustering on multilingual embeddings to select auxiliary data for PEFT adapters, outperforming linguistic-similarity baselines on multilingual benchmarks while supporting continual adaptation.
-
MKJ at SemEval-2026 Task 9: A Comparative Study of Generalist, Specialist, and Ensemble Strategies for Multilingual Polarization
A language-adaptive combination of generalist, specialist, and ensemble transformer models achieves 0.796 macro F1 and 0.826 accuracy on multilingual polarization detection across 22 languages.
- Hy-MT2: A Family of Fast, Efficient and Powerful Multilingual Translation Models in the Wild