Singapore Management University
Abstract:The proliferation of Machine Learning (ML) models and their open-source implementations has transformed Artificial Intelligence research and applications. Platforms like Hugging Face (HF) enable the development, sharing, and deployment of these models, fostering an evolving ecosystem. While previous studies have examined aspects of models hosted on platforms like HF, a comprehensive longitudinal study of how these models change remains underexplored. This study addresses this gap by utilizing both repository mining and longitudinal analysis methods to examine over 200,000 commits and 1,200 releases from over 50,000 models on HF. We replicate and extend an ML change taxonomy for classifying commits and utilize Bayesian networks to uncover patterns in commit and release activities over time. Our findings indicate that commit activities align with established data science methodologies, such as CRISP-DM, emphasizing iterative refinement and continuous improvement. Additionally, release patterns tend to consolidate significant updates, particularly in documentation, distinguishing between granular changes and milestone-based releases. Furthermore, projects with higher popularity prioritize infrastructure enhancements early in their lifecycle, and those with intensive collaboration practices exhibit improved documentation standards. These and other insights enhance the understanding of model changes on community platforms and provide valuable guidance for best practices in model maintenance.
Abstract:Background: Open-Source Pre-Trained Models (PTMs) and datasets provide extensive resources for various Machine Learning (ML) tasks, yet these resources lack a classification tailored to Software Engineering (SE) needs. Aims: We apply an SE-oriented classification to PTMs and datasets on a popular open-source ML repository, Hugging Face (HF), and analyze the evolution of PTMs over time. Method: We conducted a repository mining study. We started with a systematically gathered database of PTMs and datasets from the HF API. Our selection was refined by analyzing model and dataset cards and metadata, such as tags, and confirming SE relevance using Gemini 1.5 Pro. All analyses are replicable, with a publicly accessible replication package. Results: The most common SE task among PTMs and datasets is code generation, with a primary focus on software development and limited attention to software management. Popular PTMs and datasets mainly target software development. Among ML tasks, text generation is the most common in SE PTMs and datasets. There has been a marked increase in PTMs for SE since 2023 Q2. Conclusions: This study underscores the need for broader task coverage to enhance the integration of ML within SE practices.
Abstract:Selecting the best code solution from multiple generated ones is an essential task in code generation, which can be achieved by using some reliable validators (e.g., developer-written test cases) for assistance. Since reliable test cases are not always available and can be expensive to build in practice, researchers propose to automatically generate test cases to assess code solutions. However, when both code solutions and test cases are plausible and not reliable, selecting the best solution becomes challenging. Although some heuristic strategies have been proposed to tackle this problem, they lack a strong theoretical guarantee and it is still an open question whether an optimal selection strategy exists. Our work contributes in two ways. First, we show that within a Bayesian framework, the optimal selection strategy can be defined based on the posterior probability of the observed passing states between solutions and tests. The problem of identifying the best solution is then framed as an integer programming problem. Second, we propose an efficient approach for approximating this optimal (yet uncomputable) strategy, where the approximation error is bounded by the correctness of prior knowledge. We then incorporate effective prior knowledge to tailor code generation tasks. Both theoretical and empirical studies confirm that existing heuristics are limited in selecting the best solutions with plausible test cases. Our proposed approximated optimal strategy B4 significantly surpasses existing heuristics in selecting code solutions generated by large language models (LLMs) with LLM-generated tests, achieving a relative performance improvement by up to 50% over the strongest heuristic and 246% over the random selection in the most challenging scenarios. Our code is publicly available at https://github.com/ZJU-CTAG/B4.
Abstract:Unanticipated runtime errors, lacking predefined handlers, can abruptly terminate execution and lead to severe consequences, such as data loss or system crashes. Despite extensive efforts to identify potential errors during the development phase, such unanticipated errors remain a challenge to to be entirely eliminated, making the runtime mitigation measurements still indispensable to minimize their impact. Automated self-healing techniques, such as reusing existing handlers, have been investigated to reduce the loss coming through with the execution termination. However, the usability of existing methods is retained by their predefined heuristic rules and they fail to handle diverse runtime errors adaptively. Recently, the advent of Large Language Models (LLMs) has opened new avenues for addressing this problem. Inspired by their remarkable capabilities in understanding and generating code, we propose to deal with the runtime errors in a real-time manner using LLMs. Specifically, we propose Healer, the first LLM-assisted self-healing framework for handling runtime errors. When an unhandled runtime error occurs, Healer will be activated to generate a piece of error-handling code with the help of its internal LLM and the code will be executed inside the runtime environment owned by the framework to obtain a rectified program state from which the program should continue its execution. Our exploratory study evaluates the performance of Healer using four different code benchmarks and three state-of-the-art LLMs, GPT-3.5, GPT-4, and CodeQwen-7B. Results show that, without the need for any fine-tuning, GPT-4 can successfully help programs recover from 72.8% of runtime errors, highlighting the potential of LLMs in handling runtime errors.
Abstract:Software vulnerabilities pose significant security challenges and potential risks to society, necessitating extensive efforts in automated vulnerability detection. There are two popular lines of work to address automated vulnerability detection. On one hand, Static Application Security Testing (SAST) is usually utilized to scan source code for security vulnerabilities, especially in industries. On the other hand, deep learning (DL)-based methods, especially since the introduction of large language models (LLMs), have demonstrated their potential in software vulnerability detection. However, there is no comparative study between SAST tools and LLMs, aiming to determine their effectiveness in vulnerability detection, understand the pros and cons of both SAST and LLMs, and explore the potential combination of these two families of approaches. In this paper, we compared 15 diverse SAST tools with 12 popular or state-of-the-art open-source LLMs in detecting software vulnerabilities from repositories of three popular programming languages: Java, C, and Python. The experimental results showed that SAST tools obtain low vulnerability detection rates with relatively low false positives, while LLMs can detect up 90\% to 100\% of vulnerabilities but suffer from high false positives. By further ensembling the SAST tools and LLMs, the drawbacks of both SAST tools and LLMs can be mitigated to some extent. Our analysis sheds light on both the current progress and future directions for software vulnerability detection.
Abstract:Automated software engineering has been greatly empowered by the recent advances in Large Language Models (LLMs) for programming. While current benchmarks have shown that LLMs can perform various software engineering tasks like human developers, the majority of their evaluations are limited to short and self-contained algorithmic tasks. Solving challenging and practical programming 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 programming tasks, we introduce Bench, a benchmark that challenges LLMs to invoke multiple function calls as tools from 139 libraries and 7 domains for 1,140 fine-grained programming tasks. To evaluate LLMs rigorously, each programming task encompasses 5.6 test cases with an average branch coverage of 99%. In addition, we propose a natural-language-oriented variant of Bench, Benchi, 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.
Abstract:Besides humans and machines, Artificial Intelligence (AI) models have emerged to be another important audience of programming languages, as we come to the era of large language models (LLMs). LLMs can now excel at coding competitions and even program like developers to address various tasks, such as math calculation. Yet, the grammar and layout of existing programs are designed for humans. Particularly, abundant grammar tokens and formatting tokens are included to make the code more readable to humans. While beneficial, such a human-centric design imposes an unnecessary computational burden on LLMs where each token, either consumed or generated, consumes computational resources. To improve inference efficiency and reduce computational costs, we propose the concept of AI-oriented grammar, which aims to represent the code in a way that better suits the working mechanism of AI models. Code written with AI-oriented grammar discards formats and uses a minimum number of tokens to convey code semantics effectively. To demonstrate the feasibility of this concept, we explore and implement the first AI-oriented grammar for Python, named Simple Python (SimPy). SimPy is crafted by revising the original Python grammar through a series of heuristic rules. Programs written in SimPy maintain identical Abstract Syntax Tree (AST) structures to those in standard Python, allowing execution via a modified AST parser. In addition, we explore methods to enable existing LLMs to proficiently understand and use SimPy, and ensure the changes remain imperceptible for human developers. Compared with the original Python, SimPy not only reduces token usage by 13.5% and 10.4% for CodeLlama and GPT-4, but can also achieve equivalent, even improved, performance over the models trained on Python code.
Abstract:Just-In-Time (JIT) defect prediction aims to automatically predict whether a commit is defective or not, and has been widely studied in recent years. In general, most studies can be classified into two categories: 1) simple models using traditional machine learning classifiers with hand-crafted features, and 2) complex models using deep learning techniques to automatically extract features from commit contents. Hand-crafted features used by simple models are based on expert knowledge but may not fully represent the semantic meaning of the commits. On the other hand, deep learning-based features used by complex models represent the semantic meaning of commits but may not reflect useful expert knowledge. Simple models and complex models seem complementary to each other to some extent. To utilize the advantages of both simple and complex models, we propose a model fusion framework that adopts both early fusions on the feature level and late fusions on the decision level. We propose SimCom++ by adopting the best early and late fusion strategies. The experimental results show that SimCom++ can significantly outperform the baselines by 5.7--26.9\%. In addition, our experimental results confirm that the simple model and complex model are complementary to each other.
Abstract:The remarkable achievements of Artificial Intelligence (AI) algorithms, particularly in Machine Learning (ML) and Deep Learning (DL), have fueled their extensive deployment across multiple sectors, including Software Engineering (SE). However, due to their black-box nature, these promising AI-driven SE models are still far from being deployed in practice. This lack of explainability poses unwanted risks for their applications in critical tasks, such as vulnerability detection, where decision-making transparency is of paramount importance. This paper endeavors to elucidate this interdisciplinary domain by presenting a systematic literature review of approaches that aim to improve the explainability of AI models within the context of SE. The review canvasses work appearing in the most prominent SE & AI conferences and journals, and spans 63 papers across 21 unique SE tasks. Based on three key Research Questions (RQs), we aim to (1) summarize the SE tasks where XAI techniques have shown success to date; (2) classify and analyze different XAI techniques; and (3) investigate existing evaluation approaches. Based on our findings, we identified a set of challenges remaining to be addressed in existing studies, together with a roadmap highlighting potential opportunities we deemed appropriate and important for future work.
Abstract:We propose GNNInfer, the first automatic property inference technique for GNNs. To tackle the challenge of varying input structures in GNNs, GNNInfer first identifies a set of representative influential structures that contribute significantly towards the prediction of a GNN. Using these structures, GNNInfer converts each pair of an influential structure and the GNN to their equivalent FNN and then leverages existing property inference techniques to effectively capture properties of the GNN that are specific to the influential structures. GNNINfer then generalizes the captured properties to any input graphs that contain the influential structures. Finally, GNNInfer improves the correctness of the inferred properties by building a model (either a decision tree or linear regression) that estimates the deviation of GNN output from the inferred properties given full input graphs. The learned model helps GNNInfer extend the inferred properties with constraints to the input and output of the GNN, obtaining stronger properties that hold on full input graphs. Our experiments show that GNNInfer is effective in inferring likely properties of popular real-world GNNs, and more importantly, these inferred properties help effectively defend against GNNs' backdoor attacks. In particular, out of the 13 ground truth properties, GNNInfer re-discovered 8 correct properties and discovered likely correct properties that approximate the remaining 5 ground truth properties. Using properties inferred by GNNInfer to defend against the state-of-the-art backdoor attack technique on GNNs, namely UGBA, experiments show that GNNInfer's defense success rate is up to 30 times better than existing baselines.