Entity · paper

Reinforcement Learning Elicits Contextual Learning of Unseen Language Translation

paperactivereinforcement-learning-elicits-contextual-learning-of-unseen-language-translation-b51abe1a·1 events·first seen Jun 5, 2026

Aliases: Reinforcement Learning Elicits Contextual Learning of Unseen Language Translation

Co-occurring entities

chrF

More like this (12)

Reinforcement Learning for Language Models Multi-Task Bayesian In-Context Learning Visually Grounded Self-Reflection for Vision-Language Models via Reinforcement Learning When English Isn't the Best Teacher: Source Language Effects in Cross-Lingual In-Context Learning Latent Context Language Models Reinforcement Learning for Code On the Limits of Prompt-Conditioned Language Models as General-Purpose Learners Language-Critique Imitation Learning from Suboptimal Demonstrations ENTRAP-VL: A Taxonomic Probe for Dual Contextual Entrainment in Vision-Language Models Holonomy Memory Reinforcement Learning Same Lesson, Different Story: Cross-Lingual Reconstruction of Cultural Narratives in Large Language Models Exposure is Optional: Learning Unlike Coordination in Language Models

Recent events (1)

5arXiv · cs.CL·Jun 5, 2026·source ↗

Reinforcement learning enables meta-skill for translating unseen low-resource languages via in-context linguistic knowledge

Researchers propose an RL-based training approach for translating extremely low-resource or unseen languages by rewarding models for extracting and applying in-context linguistic knowledge (e.g., grammar books) rather than memorizing specific languages. Using chrF as a surface-level reward signal, RL-trained models outperform both in-context learning and supervised fine-tuning on completely unseen languages at test time. The work extends outcome-based RL beyond math and coding reasoning tasks, suggesting broader applicability to language learning from context.

Evaluation and Benchmarking Alignment and RLHF Reinforcement Learning Elicits Contextual Learning of Unseen Language Translation chrF