arXiv subjects

David Lo

Publications and source records attributed to David Lo.

At least 145 records · Page 8Linked to original sources

arXiv2025

Enhancing Project-Specific Code Completion by Inferring Internal API Information

Project-specific code completion is a critical task that leverages context from a project to generate accurate code. State-of-the-art methods use retrieval-augmented generation (RAG) with large language models (LLMs) and project information for code completion. However, they often struggle to incorporate internal API information, which is crucial for accuracy, especially when APIs are not explicitly imported in the file. To address this, we propose a method to infer internal API information without relying on imports. Our method extends the representation of APIs by constructing usage examples and semantic descriptions, building a knowledge base for LLMs to generate relevant completions. We also introduce ProjBench, a benchmark that avoids leaked imports and consists of large-scale real-world projects. Experiments on ProjBench and CrossCodeEval show that our approach significantly outperforms existing methods, improving code exact match by 22.72% and identifier exact match by 18.31%. Additionally, integrating our method with existing baselines boosts code match by 47.80% and identifier match by 35.55%.

cs.SE↗

arXiv2025

Do Existing Testing Tools Really Uncover Gender Bias in Text-to-Image Models?

Text-to-Image (T2I) models have recently gained significant attention due to their ability to generate high-quality images and are consequently used in a wide range of applications. However, there are concerns about the gender bias of these models. Previous studies have shown that T2I models can perpetuate or even amplify gender stereotypes when provided with neutral text prompts. Researchers have proposed automated gender bias uncovering detectors for T2I models, but a crucial gap exists: no existing work comprehensively compares the various detectors and understands how the gender bias detected by them deviates from the actual situation. This study addresses this gap by validating previous gender bias detectors using a manually labeled dataset and comparing how the bias identified by various detectors deviates from the actual bias in T2I models, as verified by manual confirmation. We create a dataset consisting of 6,000 images generated from three cutting-edge T2I models: Stable Diffusion XL, Stable Diffusion 3, and Dreamlike Photoreal 2.0. During the human-labeling process, we find that all three T2I models generate a portion (12.48% on average) of low-quality images (e.g., generate images with no face present), where human annotators cannot determine the gender of the person. Our analysis reveals that all three T2I models show a preference for generating male images, with SDXL being the most biased. Additionally, images generated using prompts containing professional descriptions (e.g., lawyer or doctor) show the most bias. We evaluate seven gender bias detectors and find that none fully capture the actual level of bias in T2I models, with some detectors overestimating bias by up to 26.95%. We further investigate the causes of inaccurate estimations, highlighting the limitations of detectors in dealing with low-quality images. Based on our findings, we propose an enhanced detector...

cs.CV↗

arXiv2025

SLICEMATE: Accurate and Scalable Static Program Slicing via LLM-Powered Agents

Static program slicing, which extracts the executable portions of a program that affect the values at a specific location, supports many software analysis tasks such as debugging and security auditing. However, traditional slicing tools rely on computationally expensive reachability analysis over dependency graphs, which struggle to scale to large programs and often fail to handle code with incomplete syntax. Recently emerged learning-based methods, while more robust to such cases, still fall short of achieving comparable performance to traditional methods on well-formed code. In this work, we propose SliceMate, a novel static program slicing solution powered by Large Language Model (LLM) agents. It bypasses the need for explicit dependency graph construction and achieving superior slicing accuracy. Concretely, SliceMate integrates three specialized agents: (1) a synthesis agent that produces candidate slices by incrementally expanding the scan scope across functions and files guided by LLM-inferred dependencies; (2) a verification agent that performs conciseness and completeness checks of the candidate slices, detecting missing or irrelevant statements; and (3) a refinement agent that repairs the slices with minimal edits in accordance with the verification results. These agents are orchestrated by a control module that ensures timely convergence and outputs high-quality slices without manual intervention. For rigorous evaluation, we construct a new and high-quality benchmark, SliceBench, comprising 2,200 manually annotated Java and Python programs, with program lengths ranging from 5 to 8,577 lines, significantly larger than those in existing slicing benchmarks. Experimental results show that SliceMate greatly outperforms both traditional and learning-based slicing tools.

cs.SE↗

arXiv2025

VulCoCo: A Simple Yet Effective Method for Detecting Vulnerable Code Clones

Code reuse is common in modern software development, but it can also spread vulnerabilities when developers unknowingly copy risky code. The code fragments that preserve the logic of known vulnerabilities are known as vulnerable code clones (VCCs). Detecting those VCCs is a critical but challenging task. Existing VCC detection tools often rely on syntactic similarity or produce coarse vulnerability predictions without clear explanations, limiting their practical utility. In this paper, we propose VulCoCo, a lightweight and scalable approach that combines embedding-based retrieval with large language model (LLM) validation. Starting from a set of known vulnerable functions, we retrieve syntactically or semantically similar candidate functions from a large corpus and use an LLM to assess whether the candidates retain the vulnerability. Given that there is a lack of reproducible vulnerable code clone benchmarks, we first construct a synthetic benchmark that spans various clone types. Our experiments on the benchmark show that VulCoCo outperforms prior state-of-the-art methods in terms of Precision@k and mean average precision (MAP). In addition, we also demonstrate VulCoCo's effectiveness in real-world projects by submitting 400 pull requests (PRs) to 284 open-source projects. Among them, 75 PRs were merged, and 15 resulted in newly published CVEs. We also provide insights to inspire future work to further improve the precision of vulnerable code clone detection.

cs.SE↗

arXiv2025

LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Ahead

Integrating Large Language Models (LLMs) into autonomous agents marks a significant shift in the research landscape by offering cognitive abilities that are competitive with human planning and reasoning. This paper explores the transformative potential of integrating Large Language Models into Multi-Agent (LMA) systems for addressing complex challenges in software engineering (SE). By leveraging the collaborative and specialized abilities of multiple agents, LMA systems enable autonomous problem-solving, improve robustness, and provide scalable solutions for managing the complexity of real-world software projects. In this paper, we conduct a systematic review of recent primary studies to map the current landscape of LMA applications across various stages of the software development lifecycle (SDLC). To illustrate current capabilities and limitations, we perform two case studies to demonstrate the effectiveness of state-of-the-art LMA frameworks. Additionally, we identify critical research gaps and propose a comprehensive research agenda focused on enhancing individual agent capabilities and optimizing agent synergy. Our work outlines a forward-looking vision for developing fully autonomous, scalable, and trustworthy LMA systems, laying the foundation for the evolution of Software Engineering 2.0.

cs.SE↗

arXiv2025

DITING: A Static Analyzer for Identifying Bad Partitioning Issues in TEE Applications

Trusted Execution Environment (TEE) enhances the security of mobile applications and cloud services by isolating sensitive code in the secure world from the non-secure normal world. However, TEE applications are still confronted with vulnerabilities stemming from bad partitioning. Bad partitioning can lead to critical security problems of TEE, such as leaking sensitive data to the normal world or being adversely affected by malicious inputs from the normal world. To address this, we propose an approach to detect partitioning issues in TEE applications. First, we conducted a survey of TEE vulnerabilities caused by bad partitioning and found that the parameters exchanged between the secure and normal worlds often contain insecure usage with bad partitioning implementation. Second, we developed a tool named DITING that can analyze data-flows of these parameters and identify their violations of security rules we defined to find bad partitioning issues. Different from existing research that only focuses on malicious input to TEE, we assess the partitioning issues more comprehensively through input/output and shared memory. Finally, we created the first benchmark targeting bad partitioning, consisting of 110 test cases. Experiments demonstrate that DITING achieves an F1 score of 0.90 in identifying bad partitioning issues.

cs.CR↗

arXiv2025

CCISolver: End-to-End Detection and Repair of Method-Level Code-Comment Inconsistency

Comments within code serve as a crucial foundation for software documentation, facilitating developers to communicate and understand the code effectively. However, code-comment inconsistency (CCI) can negatively affect software development, testing, and maintenance. Recent efforts to mitigate this issue have emerged, but existing studies often suffer from inaccurate datasets and inadequate solutions, weakening their practical effectiveness. In this study, we first conduct a quantitative analysis of existing datasets, revealing a substantial portion of sampled data are mislabeled. To address these data limitations, we introduce CCIBench, a refined dataset comprising high-quality data, to support the training and evaluation of method-level CCI methods. Furthermore, we present an innovative end-to-end LLM-based framework, CCISolver, designed to improve code quality by identifying and rectifying CCIs. Comprehensive evaluations demonstrate CCISolver's superior performance. For detection, it establishes a new state-of-the-art with an F1-score of 89.54%. In fixing task, it achieves a remarkable 18.84% relative improvement in GLEU score over the strongest baseline. This superiority is confirmed by human evaluation, where CCISolver's fixing success rate of 0.6533 significantly surpasses existing methods. Critically, in a practical end-to-end setting, CCISolver's innovative architecture is approximately 36% faster for inference than the baseline model, underscoring its scalability and real-world applicability.

cs.SE↗

arXiv2025

Characterising Bugs in Jupyter Platform

As a representative literate programming platform, Jupyter is widely adopted by developers, data analysts, and researchers for replication, data sharing, documentation, interactive data visualization, and more. Understanding the bugs in the Jupyter platform is essential for ensuring its correctness, security, and robustness. Previous studies focused on code reuse, restoration, and repair execution environment for Jupyter notebooks. However, the bugs in Jupyter notebooks' hosting platform Jupyter are not investigated. In this paper, we investigate 387 bugs in the Jupyter platform. These Jupyter bugs are classified into 11 root causes and 11 bug symptoms. We identify 14 major findings for developers. More importantly, our study opens new directions in building tools for detecting and fixing bugs in the Jupyter platform.

cs.SE↗

arXiv2025

Less is More: DocString Compression in Code Generation

The widespread use of Large Language Models (LLMs) in software engineering has intensified the need for improved model and resource efficiency. In particular, for neural code generation, LLMs are used to translate function/method signature and DocString to executable code. DocStrings which capture user re quirements for the code and used as the prompt for LLMs, often contains redundant information. Recent advancements in prompt compression have shown promising results in Natural Language Processing (NLP), but their applicability to code generation remains uncertain. Our empirical study show that the state-of-the-art prompt compression methods achieve only about 10% reduction, as further reductions would cause significant performance degradation. In our study, we propose a novel compression method, ShortenDoc, dedicated to DocString compression for code generation. Our extensive experiments on six code generation datasets, five open-source LLMs (1B to 10B parameters), and one closed-source LLM GPT-4o confirm that ShortenDoc achieves 25-40% compression while preserving the quality of generated code, outperforming other baseline methods at similar compression levels. The benefit of this research is to improve efficiency and reduce the cost while maintaining the quality of the generated code, especially when calling third-party APIs, and is able to reduce the token processing cost by 25-40%.

cs.SE↗

arXiv2025

A Closer Look into Transformer-Based Code Intelligence Through Code Transformation: Challenges and Opportunities

Transformer-based models have demonstrated state-of-the-art performance in many intelligent coding tasks such as code comment generation and code completion. Previous studies show that deep learning models are sensitive to the input variations, but few studies have systematically studied the robustness of Transformer under perturbed input code. In this work, we empirically study the effect of semantic-preserving code transformation on the performance of Transformer. Specifically, 24 and 27 code transformation strategies are implemented for two popular programming languages, Java and Python, respectively. For facilitating analysis, the strategies are grouped into five categories: block transformation, insertion/deletion transformation, grammatical statement transformation, grammatical token transformation, and identifier transformation. Experiments on three popular code intelligence tasks, including code completion, code summarization and code search, demonstrate insertion/deletion transformation and identifier transformation show the greatest impact on the performance of Transformer. Our results also suggest that Transformer based on abstract syntax trees (ASTs) shows more robust performance than the model based on only code sequence under most code transformations. Besides, the design of positional encoding can impact the robustness of Transformer under code transformation. Based on our findings, we distill some insights about the challenges and opportunities for Transformer-based code intelligence.

cs.SE↗

arXiv2025

TACLR: A Scalable and Efficient Retrieval-based Method for Industrial Product Attribute Value Identification

Product Attribute Value Identification (PAVI) involves identifying attribute values from product profiles, a key task for improving product search, recommendation, and business analytics on e-commerce platforms. However, existing PAVI methods face critical challenges, such as inferring implicit values, handling out-of-distribution (OOD) values, and producing normalized outputs. To address these limitations, we introduce Taxonomy-Aware Contrastive Learning Retrieval (TACLR), the first retrieval-based method for PAVI. TACLR formulates PAVI as an information retrieval task by encoding product profiles and candidate values into embeddings and retrieving values based on their similarity. It leverages contrastive training with taxonomy-aware hard negative sampling and employs adaptive inference with dynamic thresholds. TACLR offers three key advantages: (1) it effectively handles implicit and OOD values while producing normalized outputs; (2) it scales to thousands of categories, tens of thousands of attributes, and millions of values; and (3) it supports efficient inference for high-load industrial deployment. Extensive experiments on proprietary and public datasets validate the effectiveness and efficiency of TACLR. Further, it has been successfully deployed on the real-world e-commerce platform Xianyu, processing millions of product listings daily with frequently updated, large-scale attribute taxonomies. We release the code to facilitate reproducibility and future research at https://github.com/SuYindu/TACLR.

cs.CL↗

arXiv2025

CODE-DITING: A Reasoning-Based Metric for Functional Alignment in Code Evaluation

Trustworthy evaluation methods for code snippets play a crucial role in neural code generation. Traditional methods, which either rely on reference solutions or require executable test cases, have inherent limitation in flexibility and scalability. The recent LLM-as-Judge methodology offers a promising alternative by directly evaluating functional consistency between the problem description and the generated code. To systematically understand the landscape of these LLM-as-Judge methods, we conduct a comprehensive empirical study across three diverse datasets. Our investigation reveals the pros and cons of two categories of LLM-as-Judge methods: the methods based on general foundation models can achieve good performance but require complex prompts and lack explainability, while the methods based on reasoning foundation models provide better explainability with simpler prompts but demand substantial computational resources due to their large parameter sizes. To address these limitations, we propose CODE-DITING, a novel code evaluation method that balances accuracy, efficiency and explainability. We develop a data distillation framework that effectively transfers reasoning capabilities from DeepSeek-R1671B to our CODE-DITING 1.5B and 7B models, significantly enhancing evaluation explainability and reducing the computational cost. With the majority vote strategy in the inference process, CODE-DITING 1.5B outperforms all models with the same magnitude of parameters and achieves performance which would normally exhibit in a model with 5 times of parameter scale. CODE-DITING 7B surpasses GPT-4o and DeepSeek-V3 671B, even though it only uses 1% of the parameter volume of these large models. Further experiments show that CODEDITING is robust to preference leakage and can serve as a promising alternative for code evaluation.

cs.SE↗

arXiv2025

Defending Code Language Models against Backdoor Attacks with Deceptive Cross-Entropy Loss

Code Language Models (CLMs), particularly those leveraging deep learning, have achieved significant success in code intelligence domain. However, the issue of security, particularly backdoor attacks, is often overlooked in this process. The previous research has focused on designing backdoor attacks for CLMs, but effective defenses have not been adequately addressed. In particular, existing defense methods from natural language processing, when directly applied to CLMs, are not effective enough and lack generality, working well in some models and scenarios but failing in others, thus fall short in consistently mitigating backdoor attacks. To bridge this gap, we first confirm the phenomenon of "early learning" as a general occurrence during the training of CLMs. This phenomenon refers to that a model initially focuses on the main features of training data but may become more sensitive to backdoor triggers over time, leading to overfitting and susceptibility to backdoor attacks. We then analyze that overfitting to backdoor triggers results from the use of the cross-entropy loss function, where the unboundedness of cross-entropy leads the model to increasingly concentrate on the features of the poisoned data. Based on this insight, we propose a general and effective loss function DeCE (Deceptive Cross-Entropy) by blending deceptive distributions and applying label smoothing to limit the gradient to bounded, which prevents the model from overfitting to backdoor triggers and then enhances the security of CLMs against backdoor attacks.

cs.CR↗

arXiv2025

When Deep Learning Meets Information Retrieval-based Bug Localization: A Survey

Bug localization is a crucial aspect of software maintenance, running through the entire software lifecycle. Information retrieval-based bug localization (IRBL) identifies buggy code based on bug reports, expediting the bug resolution process for developers. Recent years have witnessed significant achievements in IRBL, propelled by the widespread adoption of deep learning (DL). To provide a comprehensive overview of the current state of the art and delve into key issues, we conduct a survey encompassing 61 IRBL studies leveraging DL. We summarize best practices in each phase of the IRBL workflow, undertake a meta-analysis of prior studies, and suggest future research directions. This exploration aims to guide further advancements in the field, fostering a deeper understanding and refining practices for effective bug localization. Our study suggests that the integration of DL in IRBL enhances the model's capacity to extract semantic and syntactic information from both bug reports and source code, addressing issues such as lexical gaps, neglect of code structure information, and cold-start problems. Future research avenues for IRBL encompass exploring diversity in programming languages, adopting fine-grained granularity, and focusing on real-world applications. Most importantly, although some studies have started using large language models for IRBL, there is still a need for more in-depth exploration and thorough investigation in this area.

cs.SE↗

arXiv2025

Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks

Large Language Models (LLMs) are advancing at an amazing speed and have become indispensable across academia, industry, and daily applications. To keep pace with the status quo, this survey probes the core challenges that the rise of LLMs poses for evaluation. We identify and analyze two pivotal transitions: (i) from task-specific to capability-based evaluation, which reorganizes benchmarks around core competencies such as knowledge, reasoning, instruction following, multi-modal understanding, and safety; and (ii) from manual to automated evaluation, encompassing dynamic dataset curation and "LLM-as-a-judge" scoring. Yet, even with these transitions, a crucial obstacle persists: the evaluation generalization issue. Bounded test sets cannot scale alongside models whose abilities grow seemingly without limit. We will dissect this issue, along with the core challenges of the above two transitions, from the perspectives of methods, datasets, evaluators, and metrics. Due to the fast evolving of this field, we will maintain a living GitHub repository (links are in each section) to crowd-source updates and corrections, and warmly invite contributors and collaborators.

cs.CL↗

arXiv2025

Why Does My Transaction Fail? A First Look at Failed Transactions on the Solana Blockchain

Solana is an emerging blockchain platform, recognized for its high throughput and low transaction costs, positioning it as a preferred infrastructure for Decentralized Finance (DeFi), Non-Fungible Tokens (NFTs), and other Web 3.0 applications. In the Solana ecosystem, transaction initiators submit various instructions to interact with a diverse range of Solana smart contracts, among which are decentralized exchanges (DEXs) that utilize automated market makers (AMMs), allowing users to trade cryptocurrencies directly on the blockchain without the need for intermediaries. Despite the high throughput and low transaction costs of Solana, the advantages have exposed Solana to bot spamming for financial exploitation, resulting in the prevalence of failed transactions and network congestion. Prior work on Solana has mainly focused on the evaluation of the performance of the Solana blockchain, particularly scalability and transaction throughput, as well as on the improvement of smart contract security, leaving a gap in understanding the characteristics and implications of failed transactions on Solana. To address this gap, we conducted a large-scale empirical study of failed transactions on Solana, using a curated dataset of over 1.5 billion failed transactions across more than 72 million blocks. Specifically, we first characterized the failed transactions in terms of their initiators, failure-triggering programs, and temporal patterns, and compared their block positions and transaction costs with those of successful transactions. We then categorized the failed transactions by the error messages in their error logs, and investigated how specific programs and transaction initiators are associated with these errors...

cs.SE↗

arXiv2025

Zero-Shot Cross-Domain Code Search without Fine-Tuning

Code search aims to retrieve semantically relevant code snippets for natural language queries. While pre-trained language models (PLMs) have shown remarkable performance in this task, they struggle in cross-domain scenarios, often requiring costly fine-tuning or facing performance drops in zero-shot settings. RAPID, which generates synthetic data for model fine-tuning, is currently the only effective method for zero-shot cross-domain code search. Despite its effectiveness, RAPID demands substantial computational resources for fine-tuning and needs to maintain specialized models for each domain, underscoring the need for a zero-shot, fine-tuning-free approach for cross-domain code search. The key to tackling zero-shot cross-domain code search lies in bridging the gaps among domains. In this work, we propose to break the query-code matching process of code search into two simpler tasks: query-comment matching and code-code matching. Our empirical study reveals the strong complementarity among the three matching schemas in zero-shot cross-domain settings, i.e., query-code, query-comment, and code-code matching. Based on the findings, we propose CodeBridge, a zero-shot, fine-tuning-free approach for cross-domain code search. Specifically, CodeBridge uses Large Language Models (LLMs) to generate comments and pseudo-code, then combines query-code, query-comment, and code-code matching via PLM-based similarity scoring and sampling-based fusion. Experimental results show that our approach outperforms the state-of-the-art PLM-based code search approaches, i.e., CoCoSoDa and UniXcoder, by an average of 21.4% and 24.9% in MRR, respectively, across three datasets. Our approach also yields results that are better than or comparable to those of the zero-shot cross-domain code search approach RAPID, which requires costly fine-tuning.

cs.SE↗

arXiv2025

BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions

Task automation has been greatly empowered by the recent advances in Large Language Models (LLMs) via Python code, where the tasks ranging from software engineering development to general-purpose reasoning. While current benchmarks have shown that LLMs can solve tasks using programs like human developers, the majority of their evaluations are limited to short and self-contained algorithmic tasks or standalone function calls. Solving challenging and practical tasks requires the capability of utilizing diverse function calls as tools to efficiently implement functionalities like data analysis and web development. In addition, using multiple tools to solve a task needs compositional reasoning by accurately understanding complex instructions. Fulfilling both of these characteristics can pose a great challenge for LLMs.To assess how well LLMs can solve challenging and practical tasks via programs, we introduce BigCodeBench, a benchmark that challenges LLMs to invoke multiple function calls as tools from 139 libraries and 7 domains for 1,140 fine-grained tasks. To evaluate LLMs rigorously, each task encompasses 5.6 test cases with an average branch coverage of 99%. In addition, we propose a natural-language-oriented variant of BigCodeBench, BigCodeBench-Instruct, that automatically transforms the original docstrings into short instructions only with essential information. Our extensive evaluation of 60 LLMs shows that LLMs are not yet capable of following complex instructions to use function calls precisely, with scores up to 60%, significantly lower than the human performance of 97%. The results underscore the need for further advancements in this area.

cs.SE↗