Reinforcement Learning Elicits Contextual Learning of Unseen Language Translation
Prior work has shown that large language models (LLMs) can translate unseen or low-resource languages by undergoing continued training or even by encoding a grammar book in their context. However, both methods typically overfit specific languages, with limited zero-shot transfer at test time. To translate extremely low-resource languages at scale, we argue that LLMs must acquire the meta-skill of utilizing in-context linguistic knowledge rather than memorizing specific languages. In this paper, we propose a reinforcement learning (RL) approach to unseen language translation given rich linguistic context, using a surface-level translation metric (chrF) as the reward. Empirically, despite t...
| Authors | Hanxu Hu, Zdeněk Šnajdr, Pinzhen Chen et al. |
|---|---|
| Primary category | cs.CL |
| Published | 4 June 2026 |
| Last updated at source | 4 June 2026 |
Connected in the knowledge graph
- HanxuHU/rl-new-languageDataset · cited by
Models and datasets referencing this paper
- HanxuHU/rl-new-languageDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.