arXiv subjects

Yuchi Ma

Publications and source records attributed to Yuchi Ma.

At least 37 records · Page 2Linked to original sources

arXiv2025

RepoTransBench: A Real-World Multilingual Benchmark for Repository-Level Code Translation

Repository-level code translation refers to translating an entire code repository from one programming language to another while preserving the functionality of the source repository. Many benchmarks have been proposed to evaluate the performance of such code translators. However, previous benchmarks mostly provide fine-grained samples, focusing at either code snippet, function, or file-level code translation. Such benchmarks do not accurately reflect real-world demands, where entire repositories often need to be translated, involving longer code length and more complex functionalities. To address this gap, we propose a new benchmark, named RepoTransBench, which is a real-world multilingual repository-level code translation benchmark featuring 1,897 real-world repository samples across 13 language pairs with automatically executable test suites. Besides, we introduce RepoTransAgent, a general agent framework to perform repository-level code translation. We evaluate both our benchmark's challenges and agent's effectiveness using several methods and backbone LLMs, revealing that repository-level translation remains challenging, where the best-performing method achieves only a 32.8% success rate. Furthermore, our analysis reveals that translation difficulty varies significantly by language pair direction, with dynamic-to-static language translation being much more challenging than the reverse direction (achieving below 10% vs. static-to-dynamic at 45-63%). Finally, we conduct a detailed error analysis and highlight current LLMs' deficiencies in repository-level code translation, which could provide a reference for further improvements. We provide the code and data at https://github.com/DeepSoftwareAnalytics/RepoTransBench.

cs.SE↗

arXiv2025

SimpleDevQA: Benchmarking Large Language Models on Development Knowledge QA

The Development Knowledge Question Answering (Dev Knowledge QA) task aims to provide natural language answers to knowledge-seeking questions during software development. To investigate its importance and to what extent it has been explored, we analyze real user-LLM dialogues from WildChat and find that: (1) The Dev Knowledge QA task accounts for 39.6% of interactions(highest among all tasks), revealing broad knowledge needs beyond code generation (32.3%). (2) Only 27.5% of real Dev Knowledge QA dialogues focus on code understanding, leaving out development knowledge-seeking. (3) Only 17.1% of real-world Dev Knowledge QA dialogues can be used for constructing a benchmark. Existing benchmarks have two primary limitations for evaluating the Dev Knowledge QA capability of LLMs. First, existing benchmarks offer a limited development knowledge scope, mainly focusing on code understanding and neglecting broader knowledge during development. Second, some benchmarks are not built from real user queries. To bridge this gap, we design a three-phase pipeline that transforms real-world dialogue into simple development knowledge-seeking QA pairs. Through this pipeline, we introduce SimpleDevQA, a multilingual benchmark derived from real user dialogues. It contains 2,740 QA pairs in three languages (English, Chinese, and Russian), and focuses on questions with unique, short, and verifiable answers for accurate and simple evaluation. Experiments show that: Code LLMs generally outperform general LLMs of similar scale; Knowledge injection with the Retrieval-Augmented Generation (RAG) strategy can boost LLM accuracy by 11.3% on average; LLMs show systematic overconfidence in Dev Knowledge QA, and the answering accuracy of LLMs shows a positive correlation with their stated confidence; Generally, LLMs with stronger code generation performance also exhibit stronger performance in Dev Knowledge QA.

cs.SE↗

arXiv2025

EffiReasonTrans: RL-Optimized Reasoning for Code Translation

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.

cs.SE↗

arXiv2025

Learning county from pixels: corn yield prediction with attention-weighted multiple instance learning

Remote sensing technology has become a promising tool in yield prediction. Most prior work employs satellite imagery for county-level corn yield prediction by spatially aggregating all pixels within a county into a single value, potentially overlooking the detailed information and valuable insights offered by more granular data. To this end, this research examines each county at the pixel level and applies multiple instance learning to leverage detailed information within a county. In addition, our method addresses the "mixed pixel" issue caused by the inconsistent resolution between feature datasets and crop mask, which may introduce noise into the model and therefore hinder accurate yield prediction. Specifically, the attention mechanism is employed to automatically assign weights to different pixels, which can mitigate the influence of mixed pixels. The experimental results show that the developed model outperforms four other machine learning models over the past five years in the U.S. corn belt and demonstrates its best performance in 2022, achieving a coefficient of determination (R2) value of 0.84 and a root mean square error (RMSE) of 0.83. This paper demonstrates the advantages of our approach from both spatial and temporal perspectives. Furthermore, through an in-depth study of the relationship between mixed pixels and attention, it is verified that our approach can capture critical feature information while filtering out noise from mixed pixels.

cs.CV↗

arXiv2025

Beyond Functional Correctness: Investigating Coding Style Inconsistencies in Large Language Models

Large language models (LLMs) have brought a paradigm shift to the field of code generation, offering the potential to enhance the software development process. However, previous research mainly focuses on the accuracy of code generation, while coding style differences between LLMs and human developers remain under-explored. In this paper, we empirically analyze the differences in coding style between the code generated by mainstream Code LLMs and the code written by human developers, and summarize coding style inconsistency taxonomy. Specifically, we first summarize the types of coding style inconsistencies by manually analyzing a large number of generation results. We then compare the code generated by Code LLMs with the code written by human programmers in terms of readability, conciseness, and robustness. The results reveal that LLMs and developers have different coding styles. Additionally, we study the possible causes of these inconsistencies and provide some solutions to alleviate the problem.

cs.SE↗

arXiv2025

Smaller but Better: Self-Paced Knowledge Distillation for Lightweight yet Effective LCMs

Large code models (LCMs) have remarkably advanced the field of code generation. Despite their impressive capabilities, they still face practical deployment issues, such as high inference costs, limited accessibility of proprietary LCMs, and adaptability issues of ultra-large LCMs. These issues highlight the critical need for more accessible, lightweight yet effective LCMs. Knowledge distillation (KD) offers a promising solution, which transfers the programming capabilities of larger, advanced LCMs to smaller, less powerful LCMs. In this paper, we propose a novel Self-Paced knOwledge DistillAtion framework, named SODA, aiming at developing lightweight yet effective student LCMs. SODA consists of three stages in one cycle: (1) Correct-and-Fault Knowledge Delivery stage aims at improving the student models capability to recognize errors while ensuring its basic programming skill during the knowledge transferring, which involves correctness-aware supervised learning and fault-aware contrastive learning methods. (2) Multi-View Feedback stage aims at measuring the quality of results generated by the student model from two views, including model-based and static tool-based measurement, for identifying the difficult questions. (3) Feedback-based Knowledge Update stage aims at updating the student model adaptively by generating new questions at different difficulty levels, in which the difficulty levels are categorized based on the feedback in the second stage. Experimental results show that SODA improves the student model by 65.96% in terms of average Pass@1, outperforming the best baseline by 29.85%. Based on the SODA framework, we develop SodaCoder, a series of lightweight yet effective LCMs, which outperform 15 LCMs with less than or equal to 16B parameters. Notably, SodaCoder-DS-6.7B, built on DeepseekCoder-6.7B, even surpasses the prominent ChatGPT on average Pass@1.

cs.SE↗

arXiv2025

Towards Mitigating API Hallucination in Code Generated by LLMs with Hierarchical Dependency Aware

Application Programming Interfaces (APIs) are crucial in modern software development. Large Language Models (LLMs) assist in automated code generation but often struggle with API hallucination, including invoking non-existent APIs and misusing existing ones in practical development scenarios. Existing studies resort to Retrieval-Augmented Generation (RAG) methods for mitigating the hallucination issue, but tend to fail since they generally ignore the structural dependencies in practical projects and do not indeed validate whether the generated APIs are available or not. To address these limitations, we propose MARIN, a framework for mitigating API hallucination in code generated by LLMs with hierarchical dependency aware. MARIN consists of two phases: Hierarchical Dependency Mining, which analyzes local and global dependencies of the current function, aiming to supplement comprehensive project context in LLMs input, and Dependency Constrained Decoding, which utilizes mined dependencies to adaptively constrain the generation process, aiming to ensure the generated APIs align with the projects specifications. To facilitate the evaluation of the degree of API hallucination, we introduce a new benchmark APIHulBench and two new metrics including Micro Hallucination Number (MiHN) and Macro Hallucination Rate (MaHR). Experiments on six state-of-the-art LLMs demonstrate that MARIN effectively reduces API hallucinations, achieving an average decrease of 67.52% in MiHN and 73.56% in MaHR compared to the RAG approach. Applied to Huaweis internal projects and two proprietary LLMs, MARIN achieves average decreases of 57.33% in MiHN and 59.41% in MaHR.

cs.SE↗

arXiv2025

OmniGIRL: A Multilingual and Multimodal Benchmark for GitHub Issue Resolution

The GitHub issue resolution task aims to resolve issues reported in repositories automatically. With advances in large language models (LLMs), this task has gained increasing attention, and several benchmarks are proposed to evaluate the issue resolution ability of LLMs. However, existing benchmarks have three main limitations. First, current benchmarks focus on a single programming language, limiting the evaluation of issues from repositories across different languages. Second, they usually cover a narrow range of domains, which may fail to represent the diversity of real-world issues. Third, existing benchmarks rely solely on textual information in issue descriptions, overlooking multimodal information such as images in issues. In this paper, we propose OmniGIRL, a GitHub Issue ResoLution benchmark that is multilingual, multimodal, and multi-domain. OmniGIRL includes 959 task instances, which are collected from repositories across four programming languages (i.e., Python, JavaScript, TypeScript, and Java) and eight different domains. Our evaluation shows that current LLMs show limited performances on OmniGIRL. Notably, the best-performing model, GPT-4o, resolves only 8.6% of the issues. Besides, we find that current LLMs struggle to resolve issues requiring understanding images. The best performance is achieved by Claude-3.5-Sonnet, which resolves only 10.5% of the issues with image information. Finally, we analyze the reasons behind current LLMs' failure on OmniGIRL, providing insights for future improvements.

cs.SE↗

arXiv2025

What to Retrieve for Effective Retrieval-Augmented Code Generation? An Empirical Study and Beyond

Repository-level code generation remains challenging due to complex code dependencies and the limitations of large language models (LLMs) in processing long contexts. While retrieval-augmented generation (RAG) frameworks are widely adopted, the effectiveness of different retrieved information sources-contextual code, APIs, and similar snippets-has not been rigorously analyzed. Through an empirical study on two benchmarks, we demonstrate that in-context code and potential API information significantly enhance LLM performance, whereas retrieved similar code often introduces noise, degrading results by up to 15%. Based on the preliminary results, we propose AllianceCoder, a novel context-integrated method that employs chain-of-thought prompting to decompose user queries into implementation steps and retrieves APIs via semantic description matching. Through extensive experiments on CoderEval and RepoExec, AllianceCoder achieves state-of-the-art performance, improving Pass@1 by up to 20% over existing approaches.

cs.SE↗

arXiv2025

HumanEvo: An Evolution-aware Benchmark for More Realistic Evaluation of Repository-level Code Generation

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.

cs.SE↗

arXiv2025

Top General Performance = Top Domain Performance? DomainCodeBench: A Multi-domain Code Generation Benchmark

With the rapid advancement of large language models (LLMs), extensive research has been conducted to investigate the code generation capabilities of LLMs. However, existing efforts primarily focus on general-domain tasks, leaving LLMs' code generation performance in real-world application domains underexplored. This raises a critical question: can a model's general-domain coding ability reliably represent its ability in specialized domains? In this paper, we introduce DomainCodeBench, a multi-domain code generation benchmark designed to systematically evaluate LLMs across 12 software application domains and 15 programming languages. DomainCodeBench contains 2,400 manually verified tasks with ground truth, human-annotated docstrings, and fine-grained dependency information to ensure more coverage of domain-specific challenges. Specifically, we first identify the most popular application domains by topic mining. Then, we curate coding tasks based on commonly used frameworks and platforms in each domain. We obtain several findings through extensive experiments on DomainCodeBench with ten mainstream LLMs. (1) Performance decoupling: experiments reveal that top general-domain models do not consistently excel in specific application domains; (2) Domain-specific weaknesses: LLMs often fail due to domain knowledge gaps and third-party library misusage; (3) Contextual enhancement: we show that augmenting prompts with domain-specific knowledge improves performance by around 38.17%, providing actionable insights for performance optimization. Our replication package, including the benchmark, source code, and experimental results, is available at https://github.com/DeepSoftwareAnalytics/DomainCodeBench.

cs.SE↗

arXiv2024

FastFixer: An Efficient and Effective Approach for Repairing Programming Assignments

Providing personalized and timely feedback for student's programming assignments is useful for programming education. Automated program repair (APR) techniques have been used to fix the bugs in programming assignments, where the Large Language Models (LLMs) based approaches have shown promising results. Given the growing complexity of identifying and fixing bugs in advanced programming assignments, current fine-tuning strategies for APR are inadequate in guiding the LLM to identify bugs and make accurate edits during the generative repair process. Furthermore, the autoregressive decoding approach employed by the LLM could potentially impede the efficiency of the repair, thereby hindering the ability to provide timely feedback. To tackle these challenges, we propose FastFixer, an efficient and effective approach for programming assignment repair. To assist the LLM in accurately identifying and repairing bugs, we first propose a novel repair-oriented fine-tuning strategy, aiming to enhance the LLM's attention towards learning how to generate the necessary patch and its associated context. Furthermore, to speed up the patch generation, we propose an inference acceleration approach that is specifically tailored for the program repair task. The evaluation results demonstrate that FastFixer obtains an overall improvement of 20.46% in assignment fixing when compared to the state-of-the-art baseline. Considering the repair efficiency, FastFixer achieves a remarkable inference speedup of 16.67 times compared to the autoregressive decoding algorithm.

cs.CY↗

arXiv2024

Agents in Software Engineering: Survey, Landscape, and Vision

In recent years, Large Language Models (LLMs) have achieved remarkable success and have been widely used in various downstream tasks, especially in the tasks of the software engineering (SE) field. We find that many studies combining LLMs with SE have employed the concept of agents either explicitly or implicitly. However, there is a lack of an in-depth survey to sort out the development context of existing works, analyze how existing works combine the LLM-based agent technologies to optimize various tasks, and clarify the framework of LLM-based agents in SE. In this paper, we conduct the first survey of the studies on combining LLM-based agents with SE and present a framework of LLM-based agents in SE which includes three key modules: perception, memory, and action. We also summarize the current challenges in combining the two fields and propose future opportunities in response to existing challenges. We maintain a GitHub repository of the related papers at: https://github.com/DeepSoftwareAnalytics/Awesome-Agent4SE.

cs.SE↗

arXiv2024

When to Stop? Towards Efficient Code Generation in LLMs with Excess Token Prevention

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 tasks 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 tasks. 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

cs.SE↗

arXiv2024

RLCoder: Reinforcement Learning for Repository-Level Code Completion

Repository-level code completion aims to generate code for unfinished code snippets within the context of a specified repository. Existing approaches mainly rely on retrieval-augmented generation strategies due to limitations in input sequence length. However, traditional lexical-based retrieval methods like BM25 struggle to capture code semantics, while model-based retrieval methods face challenges due to the lack of labeled data for training. Therefore, we propose RLCoder, a novel reinforcement learning framework, which can enable the retriever to learn to retrieve useful content for code completion without the need for labeled data. Specifically, we iteratively evaluate the usefulness of retrieved content based on the perplexity of the target code when provided with the retrieved content as additional context, and provide feedback to update the retriever parameters. This iterative process enables the retriever to learn from its successes and failures, gradually improving its ability to retrieve relevant and high-quality content. Considering that not all situations require information beyond code files and not all retrieved context is helpful for generation, we also introduce a stop signal mechanism, allowing the retriever to decide when to retrieve and which candidates to retain autonomously. Extensive experimental results demonstrate that RLCoder consistently outperforms state-of-the-art methods on CrossCodeEval and RepoEval, achieving 12.2% EM improvement over previous methods. Moreover, experiments show that our framework can generalize across different programming languages and further improve previous methods like RepoCoder. We provide the code and data at https://github.com/DeepSoftwareAnalytics/RLCoder.

cs.SE↗

arXiv2024

CodeR: Issue Resolving with Multi-Agent and Task Graphs

GitHub issue resolving recently has attracted significant attention from academia and industry. SWE-bench is proposed to measure the performance in resolving issues. In this paper, we propose CodeR, which adopts a multi-agent framework and pre-defined task graphs to Repair & Resolve reported bugs and add new features within code Repository. On SWE-bench lite, CodeR is able to solve 28.33% of issues, when submitting only once for each issue. We examine the performance impact of each design of CodeR and offer insights to advance this research direction.

cs.CL↗

arXiv2024

CoderEval: A Benchmark of Pragmatic Code Generation with Generative Pre-trained Models

Code generation models based on the pre-training and fine-tuning paradigm have been increasingly attempted by both academia and industry, resulting in well-known industrial models such as Codex, CodeGen, and PanGu-Coder. To evaluate the effectiveness of these models, multiple existing benchmarks are proposed, including only cases of generating a standalone function, i.e., a function that may invoke or access only built-in functions and standard libraries. However, non-standalone functions, which typically are not included in the existing benchmarks, constitute more than 70% of the functions in popular open-source projects, and evaluating models' effectiveness on standalone functions cannot reflect these models' effectiveness on pragmatic code generation scenarios. To help bridge the preceding gap, in this paper, we propose a benchmark named CoderEval, consisting of 230 Python and 230 Java code generation tasks carefully curated from popular real-world open-source projects and a self-contained execution platform to automatically assess the functional correctness of generated code. CoderEval supports code generation tasks from six levels of context dependency, where context refers to code elements such as types, APIs, variables, and consts defined outside the function under generation but within the dependent third-party libraries, current class, file, or project. CoderEval can be used to evaluate the effectiveness of models in generating code beyond only standalone functions. By evaluating three code generation models on CoderEval, we find that the effectiveness of these models in generating standalone functions is substantially higher than that in generating non-standalone functions. Our analysis highlights the current progress and pinpoints future directions to further improve a model's effectiveness by leveraging contextual information for pragmatic code generation.

cs.SE↗

arXiv2023

SSIF: Learning Continuous Image Representation for Spatial-Spectral Super-Resolution

Existing digital sensors capture images at fixed spatial and spectral resolutions (e.g., RGB, multispectral, and hyperspectral images), and each combination requires bespoke machine learning models. Neural Implicit Functions partially overcome the spatial resolution challenge by representing an image in a resolution-independent way. However, they still operate at fixed, pre-defined spectral resolutions. To address this challenge, we propose Spatial-Spectral Implicit Function (SSIF), a neural implicit model that represents an image as a function of both continuous pixel coordinates in the spatial domain and continuous wavelengths in the spectral domain. We empirically demonstrate the effectiveness of SSIF on two challenging spatio-spectral super-resolution benchmarks. We observe that SSIF consistently outperforms state-of-the-art baselines even when the baselines are allowed to train separate models at each spectral resolution. We show that SSIF generalizes well to both unseen spatial resolutions and spectral resolutions. Moreover, SSIF can generate high-resolution images that improve the performance of downstream tasks (e.g., land use classification) by 1.7%-7%.

cs.CV↗