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 tradeoff, 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, which also helps balance inference latency. We evaluate EffiReasonTrans on six translation pairs. Experimental results show that EffiReason-Trans 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 shows improvements of translation accuracy when integrated into agent-based frameworks. Our code and data are available athttps://github.com/DeepSoftwareAnalytics/EffiReasonTrans.

Longhui Zhang, Jiahao Wang, Meishan Zhang, GaoXiong Cao, Ensheng Shi, Mayuchi Mayuchi, Jun Yu, Honghai Liu, Jing Li, Min Zhang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Code retrieval, which retrieves code snippets based on users' natural language descriptions, is widely used by devel-opers and plays a pivotal role in real-world software development. The advent of deep learning has shifted the retrieval paradigm from lexical-based matching towards leveraging deep learning models to encode source code and queries into vector represen-tations, facilitating code retrieval according to vector similarity. Despite the effectiveness of these models, managing large-scale code database presents significant challenges. Previous research proposes deep hashing-based methods, which generate hash codes for queries and code snippets and use Hamming distance for rapid recall of code candidates. However, this approach's reliance on linear scanning of the entire code base limits its scalability. To further improve the efficiency of large-scale code retrieval, we propose a novel approach SECRET (Scalable and Efficient Code Retrieval via SegmEnTed deep hashing). SECRET converts long hash codes calculated by existing deep hashing approaches into several short hash code segments through an iterative training strategy. After training, SECRET recalls code candidates by looking up the hash tables for each segment, the time complexity of recall can thus be greatly reduced. Extensive experimental results demonstrate that SECRET can drastically reduce the retrieval time by at least 95 % while achieving comparable or even higher performance of existing deep hashing approaches. Besides, SECRET also exhibits superior performance and efficiency compared to the classical hash table-based approach known as LSH under the same number of hash tables.

To evaluate the repository-level code generation capabilities of Large Language Models (LLMs) in complex real-world software development scenarios, many evaluation methods have been developed. These methods typically leverage contextual code from the latest version of a project to assist LLMs in accurately generating the desired function. However, such evaluation methods fail to consider the dynamic evolution of software projects over time, which we refer to as evolution-ignored settings. This in turn results in inaccurate evaluation of LLMs' performance. In this paper, we conduct an empirical study to deeply understand LLMs' code generation performance within settings that reflect the evolution nature of software development. To achieve this, we first construct an evolution-aware repository-level code generation dataset, namely HumanEvo, equipped with an automated execution-based evaluation tool. Second, we manually categorize HumanEvo according to dependency levels to more comprehensively analyze the model's performance in generating functions with different dependency levels. Third, we conduct extensive experiments on HumanEvo with seven representative and diverse LLMs to verify the effectiveness of the proposed benchmark. We obtain several important findings through our experimental study. For example, we find that previous evolution-ignored evaluation methods result in inflated performance of LLMs, with performance overestimations ranging from 10.0% to 61.1% under different context acquisition methods, compared to the evolution-aware evaluation approach. Based on the findings, we give actionable suggestions for more realistic evaluation of LLMs on code generation. We also build a shared evolution-aware code generation toolbox to facilitate future research. The replication package including source code and datasets is anonymously available at https://github.Com/DeepSoftwareAnalytics/HumanEvo.

Repository-level code completion remains a challenging task for existing code large language models (code LLMs) due to their limited understanding of repository-specific context and domain knowledge. While retrieval-augmented generation (RAG) approaches have shown promise by retrieving relevant code snippets as cross-file context, they suffer from two fundamental problems: misalignment between the query and the target code in the retrieval process, and the inability of existing retrieval methods to effectively utilize the inference information. To address these challenges, we propose AlignCoder, a repository-level code completion framework that introduces a query enhancement mechanism and a reinforcement learning based retriever training method. Our approach generates multiple candidate completions to construct an enhanced query that bridges the semantic gap between the initial query and the target code. Additionally, we employ reinforcement learning to train an AlignRetriever that learns to leverage inference information in the enhanced query for more accurate retrieval. We evaluate AlignCoder on two widely-used benchmarks (CrossCodeEval and RepoEval) across five backbone code LLMs, demonstrating an 18.1% improvement in EM score compared to baselines on the CrossCodeEval benchmark. The results show that our framework achieves superior performance and exhibits high generalizability across various code LLMs and programming languages.

Large language models (LLMs) have demonstrated impressive capabilities in code generation, by leveraging retrieval-augmented generation (RAG) methods. However, the computational costs associated with LLM inference, particularly in terms of latency and energy consumption, have received limited attention in the security context. This paper introduces DrainCode, the first adversarial attack targeting the computational efficiency of RAG-based code generation systems. By strategically poisoning retrieval contexts through mutation-based approach, DrainCode forces LLMs to produce significantly longer outputs, thereby increasing GPU latency and energy consumption. We evaluate the effectiveness of DrainCode across multiple models. Our experiments show that DrainCode achieves up to a 85% increase in latency, a 49% increase in energy consumption, and more than a 3× increase in output length compared to the baseline. Furthermore, we demonstrate the generalizability of the attack across different prompting strategies and its effectiveness compared to different defenses. The results highlight DrainCode as a potential method for increasing the computational overhead of LLMs, making it useful for evaluating LLM security in resource-constrained environments. We provide code and data at https://github.com/DeepSoftwareAnalytics/DrainCode.

Repository-level code generation task involves generating code at a specified location based on unfinished code with repository context. Existing research mainly rely on retrieval-augmented generation methods to complete code. Existing work mainly investigates on improving retrieval results based on the unfinished code, but rarely pays attention to the information loss in the prompt encoding process. In this paper, we propose RepoMinCoder, a novel repository-level code generation framework that adds another round of screening and ranking based on information loss, building upon the canonical retrieval-augmented generation method. Extensive experimental results demonstrate that RepoMinCoder consistently outperforms state-of-the-art methods on public benchmark RepoEval, achieving 3.3% EM and 2.1% ES improvement over previous methods. Moreover, we conduct additional experiments to study the effect of various factors in the existing code generation pipeline, including the number of retrieval candidates, the slicing strategy of the retrieval database, and different prompting strategies.

Code generation aims to automatically generate code snippets that meet given natural language requirements and plays an important role in software development. Although Code LLMs have shown excellent performance in this domain, their long generation time poses a signification limitation in practice use. In this paper, we first conduct an in-depth preliminary study with different Code LLMs on code generation task and identify a significant efficiency issue, i.e., continual generation of excess tokens. It harms the developer productivity and leads to huge computational wastes. To address it, we introduce CodeFast, an inference acceleration approach for Code LLMs on code generation. The key idea of CodeFast is to terminate the inference process in time when unnecessary excess tokens are detected. First, we propose an automatic data construction framework to obtain training data. Then, we train a unified lightweight model GenGuard applicable to multiple programming languages to predict whether to terminate inference at the current step. Finally, we enhance Code LLM with GenGuard to accelerate its inference in code generation task. We conduct extensive experiments with CodeFast on five representative Code LLMs across four widely used code generation datasets. Experimental results show that (1) CodeFast can significantly improve the inference speed of various Code LLMs in code generation, ranging form 34% to 452%, without compromising the quality of generated code. (2) CodeFast is stable across different parameter settings and can generalize to untrained datasets. Our code and data are available at https://github.com/DeepSoftwareAnalytics/CodeFast.

Code search aims to retrieve semantically relevant code snippets for a given natural language query. Recently, many approaches employing contrastive learning have shown promising results on code representation learning and greatly improved the performance of code search. However, there is still a lot of room for improvement in using contrastive learning for code search. In this paper, we propose CoCoSoDa to effectively utilize contrastive learning for code search via two key factors in contrastive learning: data augmentation and negative samples. Specifically, soft data augmentation is to dynamically masking or replacing some tokens with their types for input sequences to generate positive samples. Momentum mechanism is used to generate large and consistent representations of negative samples in a mini-batch through maintaining a queue and a momentum encoder. In addition, multimodal contrastive learning is used to pull together representations of code-query pairs and push apart the unpaired code snippets and queries. We conduct extensive experiments to evaluate the effectiveness of our approach on a large-scale dataset with six programming languages. Experimental results show that: (1) CoCoSoDa outperforms 18 baselines and especially exceeds CodeBERT, GraphCodeBERT, and UniXcoder by 13.3%, 10.5%, and 5.9% on average MRR scores, respectively. (2) The ablation studies show the effectiveness of each component of our approach. (3) We adapt our techniques to several different pre-trained models such as RoBERTa, CodeBERT, and GraphCodeBERT and observe a significant boost in their performance in code search. (4) Our model performs robustly under different hyper-parameters. Furthermore, we perform qualitative and quantitative analyses to explore reasons behind the good performance of our model.

Code search plays a crucial role in software development, enabling developers to retrieve and reuse code using natural language queries. While the performance of code search models improves with an increase in high-quality data, obtaining such data can be challenging and expensive. Recently, large language models (LLMs) such as ChatGPT have made remarkable progress in both natural and programming language understanding and generation, offering user-friendly interaction via simple prompts. Inspired by these advancements, we propose a novel approach ChatDANCE, which utilizes high-quality and diverse augmented data generated by a large language model and leverages a filtering mechanism to eliminate low-quality augmentations. Specifically, we first propose a set of ChatGPT prompting rules that are specifically designed for source code and queries. Then, we leverage ChatGPT to rewrite code and queries based on the according prompts and then propose a filtering mechanism which trains a cross-encoder from the backbone model UniXcoder to filter out code and query pairs with low matching scores. Finally, we re-train the backbone model using the obtained high-quality augmented data. Experimental results show that ChatDANCE achieves state-of-the-art performance, improving the best baseline by 13.2% (R@1) and 7% (MRR). Surprisingly, we find that this augment-filter-retrain strategy enables the backbone model (UniXcoder) to self-grow. Moreover, extensive experiments show the effectiveness of each component and ChatDANCE has stable performance under different hyperparameter settings. In addition, we conduct qualitative and quantitative analyses to investigate why ChatDANCE works well and find that it learns a more uniform distribution of representations and effectively aligns the code and query spaces. We have made the code and data anonymously available at https://anonymous.4open.science/r/ChatDANCE.

Recently, fine-tuning pre-trained code models such as CodeBERT on downstream tasks has achieved great success in many software testing and analysis tasks. While effective and prevalent, fine-tuning the pre-trained parameters incurs a large computational cost. In this paper, we conduct an extensive experimental study to explore what happens to layer-wise pre-trained representations and their encoded code knowledge during fine-tuning. We then propose efficient alternatives to fine-tune the large pre-trained code model based on the above findings. Our experimental study shows that (1) lexical, syntactic and structural properties of source code are encoded in the lower, intermediate, and higher layers, respectively, while the semantic property spans across the entire model. (2) The process of fine-tuning preserves most of the code properties. Specifically, the basic code properties captured by lower and intermediate layers are still preserved during fine-tuning. Furthermore, we find that only the representations of the top two layers change most during fine-tuning for various downstream tasks. (3) Based on the above findings, we propose Telly to efficiently fine-tune pre-trained code models via layer freezing. The extensive experimental results on five various downstream tasks demonstrate that training parameters and the corresponding time cost are greatly reduced, while performances are similar or better.

Commit messages are important for software development and maintenance.Many neural network-based approaches have been proposed and shown promising results on automatic commit message generation.However, the generated commit messages could be repetitive or redundant.In this paper, we propose RACE, a new retrieval-augmented neural commit message generation method, which treats the retrieved similar commit as an exemplar and leverages it to generate an accurate commit message.As the retrieved commit message may not always accurately describe the content/intent of the current code diff, we also propose an exemplar guider, which learns the semantic similarity between the retrieved and current code diff and then guides the generation of commit message based on the similarity.We conduct extensive experiments on a large public dataset with five programming languages.Experimental results show that RACE can outperform all baselines.Furthermore, RACE can boost the performance of existing Seq2Seq models in commit message generation.

Source code summaries are important for program comprehension and maintenance. However, there are plenty of programs with missing, outdated, or mismatched summaries. Recently, deep learning techniques have been exploited to automatically generate summaries for given code snippets. To achieve a profound understanding of how far we are from solving this problem and provide suggestions to future research, in this paper, we conduct a systematic and in-depth analysis of 5 state-of-the-art neural code summarization models on 6 widely used BLEU variants, 4 pre-processing operations and their combinations, and 3 widely used datasets. The evaluation results show that some important factors have a great influence on the model evaluation, especially on the performance of models and the ranking among the models. However, these factors might be easily overlooked. Specifically, (1) the BLEU metric widely used in existing work of evaluating code summarization models has many variants. Ignoring the differences among these variants could greatly affect the validity of the claimed results. Besides, we discover and resolve an important and previously unknown bug in BLEU calculation in a commonly-used software package. Furthermore, we conduct human evaluations and find that the metric BLEU-DC is most correlated to human perception; (2) code preprocessing choices can have a large (from -18% to +25%) impact on the summarization performance and should not be neglected. We also explore the aggregation of pre-processing combinations and boost the performance of models; (3) some important characteristics of datasets (corpus sizes, data splitting methods, and duplication ratios) have a significant impact on model evaluation. Based on the experimental results, we give actionable suggestions for evaluating code summarization and choosing the best method in different scenarios. We also build a shared code summarization toolbox to facilitate future research.

Recently, deep learning methods have become mainstream in code search since they do better at capturing semantic correlations between code snippets and search queries and have promising performance. However, code snippets have diverse information from different dimensions, such as business logic, specific algorithm, and hardware communication, so it is hard for a single code representation module to cover all the perspectives. On the other hand, as a specific query may focus on one or several perspectives, it is difficult for a single query representation module to represent different user intents. In this paper, we propose MuCoS, a multi-model ensemble learning architecture for semantic code search. It combines several individual learners, each of which emphasizes a specific perspective of code snippets. We train the individual learners on different datasets which contain different perspectives of code information, and we use a data augmentation strategy to get these different datasets. Then we ensemble the learners to capture comprehensive features of code snippets. The experiments show that MuCoS has better results than the existing state-of-the-art methods. Our source code and data are anonymously available at https://github.com/Xzh0u/MuCoS.

Code summarization aims to generate concise natural language descriptions of source code, which can help improve program comprehension and maintenance.Recent studies show that syntactic and structural information extracted from abstract syntax trees (ASTs) is conducive to summary generation.However, existing approaches fail to fully capture the rich information in ASTs because of the large size/depth of ASTs.In this paper, we propose a novel model CAST that hierarchically splits and reconstructs ASTs.First, we hierarchically split a large AST into a set of subtrees and utilize a recursive neural network to encode the subtrees.Then, we aggregate the embeddings of subtrees by reconstructing the split ASTs to get the representation of the complete AST.Finally, AST representation, together with source code embedding obtained by a vanilla code token encoder, is used for code summarization.Extensive experiments, including the ablation study and the human evaluation, on benchmarks have demonstrated the power of CAST.To facilitate reproducibility, our code and data are available at https://github.com/ DeepSoftwareAnalytics/CAST.

Commit messages are natural language descriptions of code changes, which are important for program understanding and maintenance. However, writing commit messages manually is time-consuming and laborious, especially when the code is updated frequently. Various approaches utilizing generation or retrieval techniques have been proposed to automatically generate commit messages. To achieve a better understanding of how the existing approaches perform in solving this problem, this paper conducts a systematic and in-depth analysis of the state-of-the-art models and datasets. We find that: (1) Different variants of the BLEU metric are used in previous works, which affects the evaluation and understanding of existing methods. (2) Most existing datasets are crawled only from Java repositories while repositories in other programming languages are not sufficiently explored. (3) Dataset splitting strategies can influence the performance of existing models by a large margin. Some models show better performance when the datasets are split by commit, while other models perform better when the datasets are split by timestamp or by project. Based on our findings, we conduct a human evaluation and find the BLEU metric that best correlates with the human scores for the task. We also collect a large-scale, information-rich, and multi-language commit message dataset MCMD and evaluate existing models on this dataset. Furthermore, we conduct extensive experiments under different dataset splitting strategies and suggest the suitable models under different scenarios. Based on the experimental results and findings, we provide feasible suggestions for comprehensively evaluating commit message generation models and discuss possible future research directions. We believe this work can help practitioners and researchers better evaluate and select models for automatic commit message generation. Our source code and data are available at https://github.com/DeepSoftwareAnalytics/CommitMsgEmpirical.