Rewrite to Translate, Translate to Reward: Reinforcement Learning for Source Rewriting in Machine Translation

arXiv:2606.08011v3 Announce Type: replace-cross Abstract: Prior work has explored prompting large language models (LLMs) to rewrite source text before translation, with the goal of improving machine translation (MT) quality. However, we find that such prompt-based rewriting can degrade translation quality rather than enhance it, particularly when smaller LLMs, such as 4B-parameter models, are used. We argue that this limitation stems from the difficulty of controlling rewriting behavior through natural-language prompts alone: a rewrite is useful only if it leads to a better downstream translation, yet existing prompt-based methods do not explicitly optimize for this signal. To address this issue, we propose \textbf{RLSR} (\textbf{R}einforcement \textbf{L}earning for \textbf{S}ource \textbf{R}ewriting), a reinforcement learning framework that trains the rewriting model with a reward derived from the downstream translation-quality improvement produced by each rewrite. Experiments across six MT models and 16 language pairs show that our 4B RLSR-trained rewriting models significantly outperform both the no-rewriting baseline and same-scale prompt-based rewriting baselines, while remaining competitive with baselines that use a 235B LLM. Our models and code are available at: https://github.com/vlaks425/MT-RLSR

Abstract:Prior work has explored prompting large language models (LLMs) to rewrite source text before translation, with the goal of improving machine translation (MT) quality. However, we find that such prompt-based rewriting can degrade translation quality rather than enhance it, particularly when smaller LLMs, such as 4B-parameter models, are used. We argue that this limitation stems from the difficulty of controlling rewriting behavior through natural-language prompts alone: a rewrite is useful only if it leads to a better downstream translation, yet existing prompt-based methods do not explicitly optimize for this signal. To address this issue, we propose \textbf{RLSR} (\textbf{R}einforcement \textbf{L}earning for \textbf{S}ource \textbf{R}ewriting), a reinforcement learning framework that trains the rewriting model with a reward derived from the downstream translation-quality improvement produced by each rewrite. Experiments across six MT models and 16 language pairs show that our 4B RLSR-trained rewriting models significantly outperform both the no-rewriting baseline and same-scale prompt-based rewriting baselines, while remaining competitive with baselines that use a 235B LLM. Our models and code are available at: this https URL

Computation and Language (cs.CL); Artificial Intelligence (cs.AI)

arXiv:2606.08011 [cs.CL]

(or arXiv:2606.08011v3 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2606.08011 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

aiqbench analysis

Rewrite to Translate, Translate to Reward: Reinforcement Learning for Source Rewriting in Machine Translation

Related coverage