Translate-R1: Cost-Aware Translation Tool Use via Reinforcement Learning
Mirrored from arXiv — NLP / Computation & Language for archival readability. Support the source by reading on the original site.
Computer Science > Computation and Language
Title:Translate-R1: Cost-Aware Translation Tool Use via Reinforcement Learning
Abstract:The performance gap across languages in LLMs is well documented, and closing it natively requires pretraining or fine-tuning on corpora that, for most languages, do not exist. Translation offers an alternative: converting an input into the model's dominant language unlocks its full capabilities at once. Applying translation to every input, however, is wasteful for languages the model already handles, while leaving the choice to the model fails in the opposite way, as LLMs are overconfident and skip the tool even when they cannot understand the input. Prior work resolves this with language-specific rules, domain heuristics, language identifiers, or external routers, each requiring manual engineering. We instead learn a single policy that decides when to translate from reward alone, developing language- and domain-adaptive introspection that assesses its own comprehension and invokes translation only when it cannot solve a task natively.
Using data built by our answer-preserving translation pipeline, we continue RL on the post-trained Qwen3-4B across 22 languages in 3 resource tiers (High, Low, XLow) and 5 domains, and introduce confidence-gated GSPO for cost-sensitive tool use. The gated policy lifts reward over the baseline by +4.6 on High, +23.5 on Low, and +17.5 on XLow. Against an unconstrained policy that almost always translates, it preserves full reward at 63% of the cost and is Pareto-optimal across 87% of the cost-sensitivity range. Additionally, to simulate behavior on a completely unseen language, we create 2 synthetic languages, where our gated policy improves +18.7 over the overconfident baseline that underutilizes the tool even on these incomprehensible inputs. The policy transfers zero-shot to 9 held-out languages, and we analyze how tool use emerges over training, per language and per domain.
| Comments: | 14 pages main text plus appendix, 7 figures, 11 tables |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2606.06835 [cs.CL] |
| (or arXiv:2606.06835v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2606.06835
arXiv-issued DOI via DataCite (pending registration)
|
Access Paper:
- View PDF
- HTML (experimental)
- TeX Source
References & Citations
Bibliographic and Citation Tools
Code, Data and Media Associated with this Article
Demos
Recommenders and Search Tools
arXivLabs: experimental projects with community collaborators
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.
More from arXiv — NLP / Computation & Language
-
RECAP: Regression Evaluation for Continual Adaptation of Prompts
Jun 8
-
RASFT: Rollout-Adaptive Supervised Fine-Tuning for Reasoning
Jun 8
-
OffQ: Taming Structured Outliers in LLM Quantization by Offsetting
Jun 8
-
DEFINED: A Data-Efficient Computational Framework for Fine-Grained Creativity Assessment in Debate Scenarios
Jun 8
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.