BatCoder: Self-Supervised Bidirectional Code-Documentation Learning via Back-Translation

• URL: http://arxiv.org/abs/2602.02554v1
• Date: Fri, 30 Jan 2026 11:32:15 GMT
• Title: BatCoder: Self-Supervised Bidirectional Code-Documentation Learning via Back-Translation
• Authors: Jingwen Xu, Yiyang Lu, Zisu Huang, Changze Lv, Xiaohua Wang, Shizheng Li, Zhibo Xu, Zhengkang Guo, Zhengyuan Wang, Muzhao Tian, Xuanjing Huang, Xiaoqing Zheng,
• Abstract summary: BatCoder is a self-supervised reinforcement learning framework designed to jointly optimize code generation and documentation production.<n>A documentation is first generated from code, and then the generated documentation is used to reconstruct the original code.<n> evaluated on HumanEval and MBPP with a 7B model, BatCoder achieved 83.5% and 81.0% pass@1, outperforming strong open-source baselines.
• Score: 37.23116269029009
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Training LLMs for code-related tasks typically depends on high-quality code-documentation pairs, which are costly to curate and often scarce for niche programming languages. We introduce BatCoder, a self-supervised reinforcement learning framework designed to jointly optimize code generation and documentation production. BatCoder employs a back-translation strategy: a documentation is first generated from code, and then the generated documentation is used to reconstruct the original code. The semantic similarity between the original and reconstructed code serves as an implicit reward, enabling reinforcement learning to improve the model's performance both in generating code from documentation and vice versa. This approach allows models to be trained using only code, substantially increasing the available training examples. Evaluated on HumanEval and MBPP with a 7B model, BatCoder achieved 83.5% and 81.0% pass@1, outperforming strong open-source baselines. Moreover, the framework demonstrates consistent scaling with respect to both training corpus size and model capacity.

Related papers

• CodeBoost: Boosting Code LLMs by Squeezing Knowledge from Code Snippets with RL [28.43882967593511]
  Code large language models (LLMs) have become indispensable tools for building efficient and automated coding pipelines.<n>Existing models are typically post-trained using reinforcement learning (RL) from general-purpose LLMs using "human instruction-final answer" pairs.<n>We propose CodeBoost, a framework that enhances code LLMs purely from code snippets, without relying on human-annotated instructions.
  arXiv  Detail & Related papers  (2025-08-07T10:31:24Z)
• ReCode: Updating Code API Knowledge with Reinforcement Learning [26.63327165259632]
  Large Language Models (LLMs) exhibit remarkable code generation capabilities but falter when adapting to frequent updates in external library APIs.<n>We propose ReCode, a novel framework that mimics human programmer adaptation to API changes.<n>Our experiments demonstrate that ReCode substantially boosts LLMs' code generation performance in dynamic API scenarios.
  arXiv  Detail & Related papers  (2025-06-25T14:41:13Z)
• PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback [5.459517921633247]
  We propose a novel RRTF (Rank Responses to align Test&Teacher Feedback) framework, which can effectively and efficiently boost pre-trained large language models for code generation. Under this framework, we present PanGu-Coder2, which achieves 62.20% pass@1 on the OpenAI HumanEval benchmark.
  arXiv  Detail & Related papers  (2023-07-27T15:28:29Z)
• Generation-Augmented Query Expansion For Code Retrieval [51.20943646688115]
  We propose a generation-augmented query expansion framework. Inspired by the human retrieval process - sketching an answer before searching. We achieve new state-of-the-art results on the CodeSearchNet benchmark.
  arXiv  Detail & Related papers  (2022-12-20T23:49:37Z)
• Soft-Labeled Contrastive Pre-training for Function-level Code Representation [127.71430696347174]
  We present textbfSCodeR, a textbfSoft-labeled contrastive pre-training framework with two positive sample construction methods. Considering the relevance between codes in a large-scale code corpus, the soft-labeled contrastive pre-training can obtain fine-grained soft-labels. SCodeR achieves new state-of-the-art performance on four code-related tasks over seven datasets.
  arXiv  Detail & Related papers  (2022-10-18T05:17:37Z)
• ReACC: A Retrieval-Augmented Code Completion Framework [53.49707123661763]
  We propose a retrieval-augmented code completion framework, leveraging both lexical copying and referring to code with similar semantics by retrieval. We evaluate our approach in the code completion task in Python and Java programming languages, achieving a state-of-the-art performance on CodeXGLUE benchmark.
  arXiv  Detail & Related papers  (2022-03-15T08:25:08Z)
• CodeRetriever: Unimodal and Bimodal Contrastive Learning [128.06072658302165]
  We propose the CodeRetriever model, which combines the unimodal and bimodal contrastive learning to train function-level code semantic representations. For unimodal contrastive learning, we design a semantic-guided method to build positive code pairs based on the documentation and function name. For bimodal contrastive learning, we leverage the documentation and in-line comments of code to build text-code pairs.
  arXiv  Detail & Related papers  (2022-01-26T10:54:30Z)
• GraphCodeBERT: Pre-training Code Representations with Data Flow [97.00641522327699]
  We present GraphCodeBERT, a pre-trained model for programming language that considers the inherent structure of code. We use data flow in the pre-training stage, which is a semantic-level structure of code that encodes the relation of "where-the-value-comes-from" between variables. We evaluate our model on four tasks, including code search, clone detection, code translation, and code refinement.
  arXiv  Detail & Related papers  (2020-09-17T15:25:56Z)

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.