EffiReasonTrans: RL-Optimized Reasoning for Code Translation

• URL: http://arxiv.org/abs/2510.18863v1
• Date: Tue, 21 Oct 2025 17:55:39 GMT
• Title: EffiReasonTrans: RL-Optimized Reasoning for Code Translation
• Abstract summary: EffiReasonTrans is a training framework designed to improve translation accuracy while balancing inference latency.<n>EffiReasonTrans consistently improves translation accuracy (up to +49.2% CA and +27.8% CodeBLEU compared to the base model) while reducing the number of generated tokens.
• Score: 48.862761776440635
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Code translation is a crucial task in software development and maintenance. While recent advancements in large language models (LLMs) have improved automated code translation accuracy, these gains often come at the cost of increased inference latency, hindering real-world development workflows that involve human-in-the-loop inspection. To address this trade-off, we propose EffiReasonTrans, a training framework designed to improve translation accuracy while balancing inference latency. We first construct a high-quality reasoning-augmented dataset by prompting a stronger language model, DeepSeek-R1, to generate intermediate reasoning and target translations. Each (source code, reasoning, target code) triplet undergoes automated syntax and functionality checks to ensure reliability. Based on this dataset, we employ a two-stage training strategy: supervised fine-tuning on reasoning-augmented samples, followed by reinforcement learning to further enhance accuracy and balance inference latency. We evaluate EffiReasonTrans on six translation pairs. Experimental results show that it consistently improves translation accuracy (up to +49.2% CA and +27.8% CodeBLEU compared to the base model) while reducing the number of generated tokens (up to -19.3%) and lowering inference latency in most cases (up to -29.0%). Ablation studies further confirm the complementary benefits of the two-stage training framework. Additionally, EffiReasonTrans demonstrates improved translation accuracy when integrated into agent-based frameworks. Our code and data are available at https://github.com/DeepSoftwareAnalytics/EffiReasonTrans.

Related papers

• Incentivizing Parametric Knowledge via Reinforcement Learning with Verifiable Rewards for Cross-Cultural Entity Translation [68.85147984815778]
  We propose EA-RLVR (Entity-Anchored Reinforcement Learning with Verifiable Rewards) to incentivize the effective use of parametric knowledge.<n>EA-RLVR anchors supervision on a verifiable, entity-level reward signal and incorporates lightweight structural gates to stabilize optimization.<n>We evaluate EA-RLVR on XC-Translate and observe consistent improvements in both entity translation accuracy and out-of-domain generalization.
  arXiv  Detail & Related papers  (2026-04-18T07:15:43Z)
• Bootstrapping Code Translation with Weighted Multilanguage Exploration [22.90890448332095]
  We propose BootTrans, a bootstrapping method for code translation across languages.<n>Its key idea is to leverage the functional invariance and cross-lingual portability of test suites.<n>Our method introduces a dual-pool architecture with seed and exploration pools to progressively expand training data.
  arXiv  Detail & Related papers  (2026-01-07T01:56:44Z)
• Function-to-Style Guidance of LLMs for Code Translation [59.487054943812836]
  We propose F2STrans, a function-to-style guiding paradigm designed to improve the performance of large language models in code translation.<n>Our approach comprises two key stages: (1) Functional learning, which optimize translation correctness using high-quality source-target code pairs.<n>We introduce a novel code translation benchmark that includes up-to-date source code, extensive test cases, and manually annotated ground-truth translations.
  arXiv  Detail & Related papers  (2025-07-15T08:25:02Z)
• Enhancing Translation Accuracy of Large Language Models through Continual Pre-Training on Parallel Data [13.587157318352869]
  We propose a two-phase training approach where pre-trained large language models are continually pre-trained on parallel data. We evaluate these methods on thirteen test sets for Japanese-to-English and English-to-Japanese translation.
  arXiv  Detail & Related papers  (2024-07-03T14:23:36Z)
• CTC-based Non-autoregressive Speech Translation [51.37920141751813]
  We investigate the potential of connectionist temporal classification for non-autoregressive speech translation. We develop a model consisting of two encoders that are guided by CTC to predict the source and target texts. Experiments on the MuST-C benchmarks show that our NAST model achieves an average BLEU score of 29.5 with a speed-up of 5.67$times$.
  arXiv  Detail & Related papers  (2023-05-27T03:54:09Z)
• UZH_CLyp at SemEval-2023 Task 9: Head-First Fine-Tuning and ChatGPT Data Generation for Cross-Lingual Learning in Tweet Intimacy Prediction [3.1798318618973362]
  This paper describes the submission of UZH_CLyp for the SemEval 2023 Task 9 "Multilingual Tweet Intimacy Analysis" We achieved second-best results in all 10 languages according to the official Pearson's correlation regression evaluation measure.
  arXiv  Detail & Related papers  (2023-03-02T12:18:53Z)
• DEEP: DEnoising Entity Pre-training for Neural Machine Translation [123.6686940355937]
  It has been shown that machine translation models usually generate poor translations for named entities that are infrequent in the training corpus. We propose DEEP, a DEnoising Entity Pre-training method that leverages large amounts of monolingual data and a knowledge base to improve named entity translation accuracy within sentences.
  arXiv  Detail & Related papers  (2021-11-14T17:28:09Z)
• On the Language Coverage Bias for Neural Machine Translation [81.81456880770762]
  Language coverage bias is important for neural machine translation (NMT) because the target-original training data is not well exploited in current practice. By carefully designing experiments, we provide comprehensive analyses of the language coverage bias in the training data. We propose two simple and effective approaches to alleviate the language coverage bias problem.
  arXiv  Detail & Related papers  (2021-06-07T01:55:34Z)
• Rejuvenating Low-Frequency Words: Making the Most of Parallel Data in Non-Autoregressive Translation [98.11249019844281]
  Knowledge distillation (KD) is commonly used to construct synthetic data for training non-autoregressive translation (NAT) models. We propose reverse KD to rejuvenate more alignments for low-frequency target words. Results demonstrate that the proposed approach can significantly and universally improve translation quality.
  arXiv  Detail & Related papers  (2021-06-02T02:41:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.