Bootstrapping Code Translation with Weighted Multilanguage Exploration
On the map: Synthetic data and self-improvement for LLMs → Code and instruction data synthesis
Abstract (arXiv)
Code translation across multiple programming languages is essential yet challenging due to two vital obstacles: scarcity of parallel data paired with executable test oracles, and optimization imbalance when handling diverse language pairs. We propose BootTrans, a bootstrapping method that resolves both obstacles. Its key idea is to leverage the functional invariance and cross-lingual portability of test suites, adapting abundant pivot-language unit tests to serve as universal verification oracles for multilingual reinforcement learning (RL) training. Our method introduces a dual-pool architecture with seed and exploration pools to progressively expand training data via execution-guided experience collection. Furthermore, we design a language-aware weighting mechanism that dynamically prioritizes harder translation directions based on relative performance across sibling languages, mitigating optimization imbalance. Extensive experiments on the HumanEval-X and TransCoder-Test benchmarks demonstrate substantial improvements over baseline LLMs across all translation directions, with ablation studies validating the effectiveness of both bootstrapping and weighting components.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Code and instruction data synthesis, one of 13 directions in Synthetic data and self-improvement for LLMs. Builds on 1 of its 37 references that are in the map. First posted on arXiv 7 Jan 2026.
Builds on
1 of 37 references.
References · 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Bootstrapping Niche Multilingual Code Translation via Reinforcement Learning with Execution-Based Verifiable Supervision
- 2026CodePivot: Bootstrapping Multilingual Transpilation in LLMs via Reinforcement Learning without Parallel Corpora
- 2026Translate-R1: Cost-Aware Translation Tool Use via Reinforcement Learning
- 2025Dr. Boot: Bootstrapping Program Synthesis Language Models to Perform Repairing
- 2026Mending the Holes: Mitigating Reward Hacking in Reinforcement Learning for Multilingual Translation
- 2025On-Policy Optimization with Group Equivalent Preference for Multi-Programming Language Understanding
- 2024CHAI for LLMs: Improving Code-Mixed Translation in Large Language Models through Reinforcement Learning with AI Feedback
- 2025Seed-X: Building Strong Multilingual Translation LLM with 7B Parameters