Search

API suggestion is a critical task in modern software development, assisting programmers by predicting and recommending third-party APIs based on the current context. Recent advancements in large code models (LCMs) have shown promise in the API suggestion task. However, they mainly focus on suggesting which APIs to use, ignoring that programmers may demand more assistance while using APIs in practice including when to use the suggested APIs and how to use the APIs. To mitigate the gap, we conduct a systematic evaluation of LCMs for the API suggestion task in the paper. To facilitate our investigation, we first build a benchmark that contains a diverse collection of code snippets, covering 176 APIs used in 853 popular Java projects. Three distinct scenarios in the API suggestion task are then considered for evaluation, including (1) ``\textit{when to use}'', which aims at determining the desired position and timing for API usage; (2) ``\textit{which to use}'', which aims at identifying the appropriate API from a given library; and (3) ``\textit{how to use}'', which aims at predicting the arguments for a given API. The consideration of the three scenarios allows for a comprehensive assessment of LCMs' capabilities in suggesting APIs for developers. During the evaluation, we choose nine popular LCMs with varying model sizes for the three scenarios. We also perform an in-depth analysis of the influence of context selection on the model performance ..., Comment: This paper is accepted in ASE 2024

In recent years, spatial computing Virtual Reality (VR) has emerged as a transformative technology, offering users immersive and interactive experiences across diversified virtual environments. Users can interact with VR apps through interactable GUI elements (IGEs) on the stereoscopic three-dimensional (3D) graphical user interface (GUI). The accurate recognition of these IGEs is instrumental, serving as the foundation of many software engineering tasks, including automated testing and effective GUI search. The most recent IGE detection approaches for 2D mobile apps typically train a supervised object detection model based on a large-scale manually-labeled GUI dataset, usually with a pre-defined set of clickable GUI element categories like buttons and spinners. Such approaches can hardly be applied to IGE detection in VR apps, due to a multitude of challenges including complexities posed by open-vocabulary and heterogeneous IGE categories, intricacies of context-sensitive interactability, and the necessities of precise spatial perception and visual-semantic alignment for accurate IGE detection results. Thus, it is necessary to embark on the IGE research tailored to VR apps. In this paper, we propose the first zero-shot cOntext-sensitive inteRactable GUI ElemeNT dEtection framework for virtual Reality apps, named Orienter. By imitating human behaviors, Orienter observes and understands the semantic contexts of VR app scenes first, before performing the detection. The detection process is iterated within a feedback-directed validation and reflection loop. Specifically, Orienter contains three components, including (1) Semantic context comprehension, (2) Reflection-directed IGE candidate detection, and (3) Context-sensitive interactability classification. Extensive experiments demonstrate that Orienter is more effective than the state-of-the-art GUI element detection approaches.

In recent years, the application of large language models (LLMs) to code-related tasks has gained significant attention. However, existing evaluation benchmarks often focus on limited scenarios, such as code generation or completion, which do not reflect the diverse challenges developers face in real-world contexts. To address this, we introduce ComplexCodeEval, a benchmark designed to assess LCMs in various development tasks, including code generation, completion, API recommendation, and test case generation. It includes 3,897 Java samples and 7,184 Python samples from high-star GitHub repositories, each annotated with function signatures, docstrings, and API references to simulate real development environments. Our experiments across ten LCMs reveal that context improves performance and that data leakage can lead to overestimation, highlighting the need for more accurate evaluations., Comment: Accepted by the 39th IEEE/ACM International Conference on Automated Software Engineering (ASE 2024)

The code written by developers usually suffers from efficiency problems and contain various performance bugs. These inefficiencies necessitate the research of automated refactoring methods for code optimization. Early research in code optimization employs rule-based methods and focuses on specific inefficiency issues, which are labor-intensive and suffer from the low coverage issue. Recent work regards the task as a sequence generation problem, and resorts to deep learning (DL) techniques such as large language models (LLMs). These methods typically prompt LLMs to directly generate optimized code. Although these methods show state-of-the-art performance, such one-step generation paradigm is hard to achieve an optimal solution. First, complex optimization methods such as combinatorial ones are hard to be captured by LLMs. Second, the one-step generation paradigm poses challenge in precisely infusing the knowledge required for effective code optimization within LLMs, resulting in under-optimized code.To address these problems, we propose to model this task from the search perspective, and propose a search-based LLMs framework named SBLLM that enables iterative refinement and discovery of improved optimization methods. SBLLM synergistically integrate LLMs with evolutionary search and consists of three key components: 1) an execution-based representative sample selection part that evaluates the fitness of each existing optimized code and prioritizes promising ones to pilot the generation of improved code; 2) an adaptive optimization pattern retrieval part that infuses targeted optimization patterns into the model for guiding LLMs towards rectifying and progressively enhancing their optimization methods; and 3) a genetic operator-inspired chain-of-thought prompting part that aids LLMs in combining different optimization methods and generating improved optimization methods., Comment: Accepted by 2025 IEEE/ACM 47th International Conference on Software Engineering (ICSE'25)

Large code models (LCMs) have remarkably advanced the field of code intelligence. Despite their impressive capabilities, they still face practical employment challenges, such as high costs, limited accessibility of proprietary LCMs, and adaptability issues of ultra-large LCMs. These challenges highlight the critical need for more accessible, lightweight yet effective LCMs. In this paper, we propose IterKD, an Iter Knowledge Distillation framework, which aims at continually transferring the programming capabilities of larger, advanced LCMs (Teacher) to smaller, less powerful LCMs (Student). IterKD 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; (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 last stage. By performing the training cycle iteratively, the student model is continuously refined through learning more advanced programming skills from the teacher model. Finally, based on the proposed IterKD framework, we develop a lightweight yet effective LCM, named IterCoder, which is built upon CodeLlama-7B. Experimental results show that IterCoder achieves a Pass@1 score of 65.2 on the HumanEval benchmark, outperforming over-30B-sized LCMs by an average of 47.51% and surpassing comparable-sized LCMs by an average of 118.47%.

With the growing reliance on automated code completion tools in software development, the need for robust evaluation benchmarks has become critical. However, existing benchmarks focus more on code generation tasks in function and class level and provide rich text description to prompt the model. By contrast, such descriptive prompt is commonly unavailable in real development and code completion can occur in wider range of situations such as in the middle of a function or a code block. These limitations makes the evaluation poorly align with the practical scenarios of code completion tools. In this paper, we propose RepoMasterEval, a novel benchmark for evaluating code completion models constructed from real-world Python and TypeScript repositories. Each benchmark datum is generated by masking a code snippet (ground truth) from one source code file with existing test suites. To improve test accuracy of model generated code, we employ mutation testing to measure the effectiveness of the test cases and we manually crafted new test cases for those test suites with low mutation score. Our empirical evaluation on 6 state-of-the-art models shows that test argumentation is critical in improving the accuracy of the benchmark and RepoMasterEval is able to report difference in model performance in real-world scenarios. The deployment of RepoMasterEval in a collaborated company for one month also revealed that the benchmark is useful to give accurate feedback during model training and the score is in high correlation with the model's performance in practice. Based on our findings, we call for the software engineering community to build more LLM benchmarks tailored for code generation tools taking the practical and complex development environment into consideration.

Code generation, the task of producing source code from prompts, has seen significant advancements with the advent of pre-trained large language models (PLMs). Despite these achievements, there lacks a comprehensive taxonomy of weaknesses about the benchmark and the generated code, which risks the community's focus on known issues at the cost of under-explored areas. Our systematic study aims to fill this gap by evaluating five state-of-the-art PLMs: three larger models, CodeGen2.5 with 7 billion parameters, CodeGeeX2 with 6 billion parameters, GPT-4 Turbo, and two smaller ones, UnixCoder with 110 million parameters and CodeT5 base with 220 million parameters, across three popular datasets, CoNaLa, HumanEval Plus, and DS-1000. We assess the quality of generated code using match-based and execution-based metrics, then conduct thematic analysis to develop a taxonomy of nine types of weaknesses. We dissected weakness distributions in both larger and smaller models, applying an extensive methodology that encompasses model-specific as well as collective analysis (union and intersection) across models. Our research uncovers three salient findings: 1. In the CoNaLa dataset, inaccurate prompts are a notable problem, causing all large models to fail in 26.84% of cases, with even higher failure rates of 40% for smaller models; 2. Missing pivotal semantics is a pervasive issue across benchmarks, with one or more large models omitting key semantics in 65.78% of CoNaLa tasks, and similarly high occurrences in HumanEval Plus (66.09%) and DS-1000 (80.51%); 3. All models struggle with proper API usage, a challenge amplified by vague or complex prompts. Our findings aim to steer researchers towards addressing specific weaknesses and challenges in code generation. Furthermore, our annotations can offer a targeted benchmark subset for detailed analysis.

Large Language Model-based (LLM-based) Text-to-SQL methods have achieved important progress in generating SQL queries for real-world applications. When confronted with table content-aware questions in real-world scenarios, ambiguous data content keywords and non-existent database schema column names within the question leads to the poor performance of existing methods. To solve this problem, we propose a novel approach towards Table Content-aware Text-to-SQL with Self-Retrieval (TCSR-SQL). It leverages LLM's in-context learning capability to extract data content keywords within the question and infer possible related database schema, which is used to generate Seed SQL to fuzz search databases. The search results are further used to confirm the encoding knowledge with the designed encoding knowledge table, including column names and exact stored content values used in the SQL. The encoding knowledge is sent to obtain the final Precise SQL following multi-rounds of generation-execution-revision process. To validate our approach, we introduce a table-content-aware, question-related benchmark dataset, containing 1,692 question-SQL pairs. Comprehensive experiments conducted on this benchmark demonstrate the remarkable performance of TCSR-SQL, achieving an improvement of at least 13.7% in execution accuracy compared to other state-of-the-art methods.

The quality of Virtual Reality (VR) apps is vital, particularly the rendering quality of the VR Graphical User Interface (GUI). Different from traditional 2D apps, VR apps create a 3D digital scene for users, by rendering two distinct 2D images for the user's left and right eyes, respectively. Stereoscopic visual inconsistency (denoted as "SVI") issues, however, undermine the rendering process of the user's brain, leading to user discomfort and even adverse health effects. Such issues commonly exist but remain underexplored. We conduct an empirical analysis on 282 SVI bug reports from 15 VR platforms, summarizing 15 types of manifestations. The empirical analysis reveals that automatically detecting SVI issues is challenging, mainly because: (1) lack of training data; (2) the manifestations of SVI issues are diverse, complicated, and often application-specific; (3) most accessible VR apps are closed-source commercial software. Existing pattern-based supervised classification approaches may be inapplicable or ineffective in detecting the SVI issues. To counter these challenges, we propose an unsupervised black-box testing framework named StereoID to identify the stereoscopic visual inconsistencies, based only on the rendered GUI states. StereoID generates a synthetic right-eye image based on the actual left-eye image and computes distances between the synthetic right-eye image and the actual right-eye image to detect SVI issues. We propose a depth-aware conditional stereo image translator to power the image generation process, which captures the expected perspective shifts between left-eye and right-eye images. We build a large-scale unlabeled VR stereo screenshot dataset with larger than 171K images from 288 real-world VR apps for experiments. After substantial experiments, StereoID demonstrates superior performance for detecting SVI issues in both user reports and wild VR apps., Comment: This work has been accepted at the ACM International Conference on the Foundations of Software Engineering (FSE) 2024, Porto de Galinhas, Brazil. DOI: https://doi.org/10.1145/3660803

Over the past decade, modern code review (MCR) has been deemed as a crucial practice of software quality assurance, which is applied to improve software quality and transfer development knowledge within a software team. Despite its importance, MCR is often a complicated and time-consuming activity for practitioners. In recent years, many studies that are dedicated to the comprehension and the improvement of MCR have been explored so that the MCR activity can be carried out more conveniently and efficiently. To provide researchers and practitioners a clear understanding of the current research status on MCR, this paper conducts a systematic literature review of the past years. Given the collected 231 surveyed papers, this paper makes the following five contributions: First, we analyze the research trends of related MCR studies. Second, we provide a taxonomy for the current MCR, encompassing both Improvement Techniques and Understanding Studies. Third, we present the concrete research progress of each novel MCR methodology and prototype tool. Fourth, we exploit the main empirical insights from empirical study and user study that are helpful to improve MCR. Finally, we sum up unsolved challenges and outline several possible research opportunities in the future., Comment: 62 pages

As Large Language Models (LLMs), including ChatGPT and analogous systems, continue to advance, their robust natural language processing capabilities and diverse applications have garnered considerable attention. Nonetheless, despite the increasing acknowledgment of the convergence of Artificial Intelligence (AI) and Software Engineering (SE), there is a lack of studies involving the impact of this convergence on the practices and perceptions of software developers. Understanding how software developers perceive and engage with AI tools, such as ChatGPT, is essential for elucidating the impact and potential challenges of incorporating AI-driven tools in the software development process. In this paper, we conducted a survey with 207 software developers to understand the impact of ChatGPT on software quality, productivity, and job satisfaction. Furthermore, the study delves into developers' expectations regarding future adaptations of ChatGPT, concerns about potential job displacement, and perspectives on regulatory interventions., Comment: 31 pages, 9 figures

In the field of code intelligence, effectively modeling long-range code poses a significant challenge. Existing pre-trained language models (PLMs) such as UniXcoder have achieved remarkable success, but they still face difficulties with long code inputs. This is mainly due to their limited capacity to maintain contextual continuity and memorize the key information over long-range code. To alleviate the difficulties, we propose EXPO, a framework for EXtending Pre-trained language models for lOng-range code. EXPO incorporates two innovative memory mechanisms we propose in this paper: Bridge Memory and Hint Memory. Bridge Memory uses a tagging mechanism to connect disparate snippets of long-range code, helping the model maintain contextual coherence. Hint Memory focuses on crucial code elements throughout the global context, such as package imports, by integrating a kNN attention layer to adaptively select the relevant code elements. This dual-memory approach bridges the gap between understanding local code snippets and maintaining global code coherence, thereby enhancing the model overall comprehension of long code sequences. We validate the effectiveness of EXPO on five popular pre-trained language models such as UniXcoder and two code intelligence tasks including API recommendation and vulnerability detection. Experimental results demonstrate that EXPO significantly improves the pre-training language models., Comment: Accepted by ISSTA 2024

The rapid advancement of deep learning has led to the development of Large Language Models (LLMs). In the field of vulnerability repair, previous research has leveraged rule-based fixing, pre-trained models, and LLM's prompt engineering. However, existing approaches have limitations in terms of the integration of code structure with error types. Besides, due to certain features of C/C++ language, vulnerability repair in C/C++ proves to be exceptionally challenging. To address these challenges, we propose NAVRepair, a novel framework that combines the node-type information extracted from Abstract Syntax Trees (ASTs) with error types, specifically targeting C/C++ vulnerabilities. Specifically, our approach employs type analysis to localize the minimum edit node (MEN) and customizes context information collection based on different error types. In the offline stage, NAVRepair parses code patches to locate MENs and designs rules to extract relevant contextual information for each MEN type. In the online repairing stage, it analyzes the suspicious code, combines it with vulnerability type templates derived from the Common Weakness Enumeration (CWE), and generates targeted repair prompts. We evaluate NAVRepair on multiple popular LLMs and demonstrate its effectiveness in improving the performance of code vulnerability repair. Notably, our framework is independent of any specific LLMs and can quickly adapt to new vulnerability types. Extensive experiments validate that NAVRepair achieves excellent results in assisting LLMs to accurately detect and fix C/C++ vulnerabilities. We achieve a 26% higher accuracy compared to an existing LLM-based C/C++ vulnerability repair method. We believe our node type-aware approach has promising application prospects for enhancing real-world C/C++ code security.

Code generation aims to synthesize code and fulfill functional requirements based on natural language (NL) specifications, which can greatly improve development efficiency. In the era of large language models (LLMs), large code models (LCMs) have been recently proposed to generate source code. LCMs can generate highly feasible solutions for programming problems described in natural language. Despite the effectiveness, we observe a noticeable multilingual bias in the generation performance of LCMs. Specifically, LCMs demonstrate proficiency in generating solutions when provided with instructions in English, yet may falter when faced with semantically equivalent instructions in other NLs such as Chinese. Moreover, the ability of LCMs to generate code exhibits variety across different programming languages (PLs), such as Python and C++. The observed phenomenon indicates the presence of multi-lingual bias within the generative capabilities of LCMs, which has remained unexplored. In this paper, we aim to investigate the multi-lingual bias that exists in current LCMs. First, we initiate our investigation by constructing the first multi-lingual evaluation benchmark X-HumanEval-X, enabling us to systematically evaluate the extent of multi-lingual bias that exists in current LCMs. In our large-scale experiments on nine popular LCMs, we observe a pronounced multi-lingual bias of LCMs in code generation, including multi-NL and multi-PL bias. Specifically, when using Chinese instructions, the code generation capabilities of LCMs decrease by at least 13% in terms of the Pass@1 metric. Furthermore, LCMs perform variously across different programming languages, e.g., the performance gap between Python and C++ reaches as high as 20.9%. ..., Comment: 12 pages

Deep Learning (DL)-based methods have proven to be effective for software vulnerability detection, with a potential for substantial productivity enhancements for detecting vulnerabilities. Current methods mainly focus on detecting single functions (i.e., intra-procedural vulnerabilities), ignoring the more complex inter-procedural vulnerability detection scenarios in practice. For example, developers routinely engage with program analysis to detect vulnerabilities that span multiple functions within repositories. In addition, the widely-used benchmark datasets generally contain only intra-procedural vulnerabilities, leaving the assessment of inter-procedural vulnerability detection capabilities unexplored. To mitigate the issues, we propose a repository-level evaluation system, named \textbf{VulEval}, aiming at evaluating the detection performance of inter- and intra-procedural vulnerabilities simultaneously. Specifically, VulEval consists of three interconnected evaluation tasks: \textbf{(1) Function-Level Vulnerability Detection}, aiming at detecting intra-procedural vulnerability given a code snippet; \textbf{(2) Vulnerability-Related Dependency Prediction}, aiming at retrieving the most relevant dependencies from call graphs for providing developers with explanations about the vulnerabilities; and \textbf{(3) Repository-Level Vulnerability Detection}, aiming at detecting inter-procedural vulnerabilities by combining with the dependencies identified in the second task. VulEval also consists of a large-scale dataset, with a total of 4,196 CVE entries, 232,239 functions, and corresponding 4,699 repository-level source code in C/C++ programming languages. Our analysis highlights the current progress and future directions for software vulnerability detection., Comment: 12 pages

Recently, there has been a growing interest in automatic software vulnerability detection. Pre-trained model-based approaches have demonstrated superior performance than other Deep Learning (DL)-based approaches in detecting vulnerabilities. However, the existing pre-trained model-based approaches generally employ code sequences as input during prediction, and may ignore vulnerability-related structural information, as reflected in the following two aspects. First, they tend to fail to infer the semantics of the code statements with complex logic such as those containing multiple operators and pointers. Second, they are hard to comprehend various code execution sequences, which is essential for precise vulnerability detection. To mitigate the challenges, we propose a Structured Natural Language Comment tree-based vulnerAbiLity dEtection framework based on the pre-trained models, named SCALE. The proposed Structured Natural Language Comment Tree (SCT) integrates the semantics of code statements with code execution sequences based on the Abstract Syntax Trees (ASTs). Specifically, SCALE comprises three main modules: (1) Comment Tree Construction, which aims at enhancing the model's ability to infer the semantics of code statements by first incorporating Large Language Models (LLMs) for comment generation and then adding the comment node to ASTs. (2) Structured Natural Language Comment Tree Construction}, which aims at explicitly involving code execution sequence by combining the code syntax templates with the comment tree. (3) SCT-Enhanced Representation, which finally incorporates the constructed SCTs for well capturing vulnerability patterns., Comment: Accepted by ISSTA 2024

Sparse models, including sparse Mixture-of-Experts (MoE) models, have emerged as an effective approach for scaling Transformer models. However, they often suffer from computational inefficiency since a significant number of parameters are unnecessarily involved in computations via multiplying values by zero or low activation values. To address this issue, we present \tool, a novel MoE designed to enhance both the efficacy and efficiency of sparse MoE models. \tool leverages small experts and a threshold-based router to enable tokens to selectively engage only essential parameters. Our extensive experiments on language modeling and machine translation tasks demonstrate that \tool can enhance model performance while decreasing the computation load at MoE layers by over 50\% without sacrificing performance. Furthermore, we present the versatility of \tool by applying it to dense models, enabling sparse computation during inference. We provide a comprehensive analysis and make our code available at https://github.com/ysngki/XMoE., Comment: ACL2024 Findings

Automatic API method recommendation is an essential task of code intelligence, which aims to suggest suitable APIs for programming queries. Existing approaches can be categorized into two primary groups: retrieval-based and learning-based approaches. Although these approaches have achieved remarkable success, they still come with notable limitations. The retrieval-based approaches rely on the text representation capabilities of embedding models, while the learning-based approaches require extensive task-specific labeled data for training. To mitigate the limitations, we propose APIGen, a generative API recommendation approach through enhanced in-context learning (ICL). APIGen involves two main components: (1) Diverse Examples Selection. APIGen searches for similar posts to the programming queries from the lexical, syntactical, and semantic perspectives, providing more informative examples for ICL. (2) Guided API Recommendation. APIGen enables large language models (LLMs) to perform reasoning before generating API recommendations, where the reasoning involves fine-grained matching between the task intent behind the queries and the factual knowledge of the APIs. With the reasoning process, APIGen makes recommended APIs better meet the programming requirement of queries and also enhances the interpretability of results. We compare APIGen with four existing approaches on two publicly available benchmarks. Experiments show that APIGen outperforms the best baseline CLEAR by 105.8% in method-level API recommendation and 54.3% in class-level API recommendation in terms of SuccessRate@1. Besides, APIGen achieves an average 49.87% increase compared to the zero-shot performance of popular LLMs such as GPT-4 in method-level API recommendation regarding the SuccessRate@3 metric., Comment: To appear in the proceedings of the 31st IEEE International Conference on Software Analysis, Evolution, and Reengineering (SANER 2024)

Open-Source Software (OSS) vulnerabilities bring great challenges to the software security and pose potential risks to our society. Enormous efforts have been devoted into automated vulnerability detection, among which deep learning (DL)-based approaches have proven to be the most effective. However, the current labeled data present the following limitations: (1) Tangled Patches: Developers may submit code changes unrelated to vulnerability fixes within patches, leading to tangled patches. (2) Lacking Inter-procedural Vulnerabilities: The existing vulnerability datasets typically contain function-level and file-level vulnerabilities, ignoring the relations between functions, thus rendering the approaches unable to detect the inter-procedural vulnerabilities. (3) Outdated Patches: The existing datasets usually contain outdated patches, which may bias the model during training. To address the above limitations, in this paper, we propose an automated data collection framework and construct the first repository-level high-quality vulnerability dataset named ReposVul. The proposed framework mainly contains three modules: (1) A vulnerability untangling module, aiming at distinguishing vulnerability-fixing related code changes from tangled patches, in which the Large Language Models (LLMs) and static analysis tools are jointly employed. (2) A multi-granularity dependency extraction module, aiming at capturing the inter-procedural call relationships of vulnerabilities, in which we construct multiple-granularity information for each vulnerability patch, including repository-level, file-level, function-level, and line-level. (3) A trace-based filtering module, aiming at filtering the outdated patches, which leverages the file path trace-based filter and commit time trace-based filter to construct an up-to-date dataset., Comment: Accepted by ICSE 2024 Industry Challenge Track

Vulnerability detection is a crucial component in the software development lifecycle. Existing vulnerability detectors, especially those based on deep learning (DL) models, have achieved high effectiveness. Despite their capability of detecting vulnerable code snippets from given code fragments, the detectors are typically unable to further locate the fine-grained information pertaining to the vulnerability, such as the precise vulnerability triggering locations.In this paper, we propose VULEXPLAINER, a tool for automatically locating vulnerability-critical code lines from coarse-level vulnerable code snippets reported by DL-based detectors.Our approach takes advantage of the code structure and the semantics of the vulnerabilities. Specifically, we leverage program slicing to get a set of critical program paths containing vulnerability-triggering and vulnerability-dependent statements and rank them to pinpoint the most important one (i.e., sub-graph) as the data flow associated with the vulnerability. We demonstrate that VULEXPLAINER performs consistently well on four state-of-the-art graph-representation(GP)-based vulnerability detectors, i.e., it can flag the vulnerability-triggering code statements with an accuracy of around 90% against eight common C/C++ vulnerabilities, outperforming five widely used GNN-based explanation approaches. The experimental results demonstrate the effectiveness of VULEXPLAINER, which provides insights into a promising research line: integrating program slicing and deep learning for the interpretation of vulnerable code fragments.

Pre-trained code models have recently achieved substantial improvements in many code intelligence tasks. These models are first pre-trained on large-scale unlabeled datasets in a task-agnostic manner using self-supervised learning, and then fine-tuned on labeled datasets in downstream tasks. However, the labeled datasets are usually limited in size (i.e., human intensive efforts), which may hinder the performance of pre-trained code models in specific tasks. To mitigate this, one possible solution is to leverage the large-scale unlabeled data in the tuning stage by pseudo-labeling. However, directly employing the pseudo-labeled data can bring a large amount of noise, i.e., incorrect labels, leading to suboptimal performance. How to effectively leverage the noisy pseudo-labeled data is a challenging yet under-explored problem.In this paper, we propose a novel approach named HINT to improve pre-trained code models with large-scale unlabeled datasets by better utilizing the pseudo-labeled data. HINT includes two main modules: HybrId pseudo-labeled data selection and Noise-tolerant Training. In the hybrid pseudo-data selection module, considering the robustness issue, apart from directly measuring the quality of pseudo labels through training loss, we further propose to employ a retrieval-based method to filter low-quality pseudo-labeled data. The noise-tolerant training module aims to further mitigate the influence of errors in pseudo labels by training the model with a noise-tolerant loss function and by regularizing the consistency of model predictions.The experimental results show that HINT can better leverage those unlabeled data in a task-specific way and provide complementary benefits for pre-trained models, e.g., improving the best baseline model by 15.33%, 16.50%, and 8.98% on code summarization, defect detection, and assertion generation, respectively., Comment: Accepted by ICSE 2024

With recent advancements in Large Multimodal Models (LMMs) across various domains, a novel prompting method called visual referring prompting has emerged, showing significant potential in enhancing human-computer interaction within multimodal systems. This method offers a more natural and flexible approach to human interaction with these systems compared to traditional text descriptions or coordinates. However, the categorization of visual referring prompting remains undefined, and its impact on the performance of LMMs has yet to be formally examined. In this study, we conduct the first comprehensive analysis of LMMs using a variety of visual referring prompting strategies. We introduce a benchmark dataset called VRPTEST, comprising 3 different visual tasks and 2,275 images, spanning diverse combinations of prompt strategies. Using VRPTEST, we conduct a comprehensive evaluation of eight versions of prominent open-source and proprietary foundation models, including two early versions of GPT-4V. We develop an automated assessment framework based on software metamorphic testing techniques to evaluate the accuracy of LMMs without the need for human intervention or manual labeling. We find that the current proprietary models generally outperform the open-source ones, showing an average accuracy improvement of 22.70%; however, there is still potential for improvement. Moreover, our quantitative analysis shows that the choice of prompt strategy significantly affects the accuracy of LMMs, with variations ranging from -17.5% to +7.3%. Further case studies indicate that an appropriate visual referring prompting strategy can improve LMMs' understanding of context and location information, while an unsuitable one might lead to answer rejection. We also provide insights on minimizing the negative impact of visual referring prompting on LMMs., Comment: 13 pages

Python is widely used in the open-source community, largely owing to the extensive support from diverse third-party libraries within the PyPI ecosystem. Nevertheless, the utilization of third-party libraries can potentially lead to conflicts in dependencies, prompting researchers to develop dependency conflict detectors. Moreover, endeavors have been made to automatically infer dependencies. These approaches focus on version-level checks and inference, based on the assumption that configurations of libraries in the PyPI ecosystem are correct. However, our study reveals that this assumption is not universally valid, and relying solely on version-level checks proves inadequate in ensuring compatible run-time environments. In this paper, we conduct an empirical study to comprehensively study the configuration issues in the PyPI ecosystem. Specifically, we propose PyConf, a source-level detector, for detecting potential configuration issues. PyConf employs three distinct checks, targeting the setup, packing, and usage stages of libraries, respectively. To evaluate the effectiveness of the current automatic dependency inference approaches, we build a benchmark called VLibs, comprising library releases that pass all three checks of PyConf. We identify 15 kinds of configuration issues and find that 183,864 library releases suffer from potential configuration issues. Remarkably, 68% of these issues can only be detected via the source-level check. Our experiment results show that the most advanced automatic dependency inference approach, PyEGo, can successfully infer dependencies for only 65% of library releases. The primary failures stem from dependency conflicts and the absence of required libraries in the generated configurations. Based on the empirical results, we derive six findings and draw two implications for open-source developers and future research in automatic dependency inference., Comment: This paper has been accepted by ICSE 2024

Large language models (LLMs) have shown promise as automated evaluators for assessing the quality of answers generated by AI systems. However, these LLM-based evaluators exhibit position bias, or inconsistency, when used to evaluate candidate answers in pairwise comparisons, favoring either the first or second answer regardless of content. To address this limitation, we propose PORTIA, an alignment-based system designed to mimic human comparison strategies to calibrate position bias in a lightweight yet effective manner. Specifically, PORTIA splits the answers into multiple segments, aligns similar content across candidate answers, and then merges them back into a single prompt for evaluation by LLMs. We conducted extensive experiments with six diverse LLMs to evaluate 11,520 answer pairs. Our results show that PORTIA markedly enhances the consistency rates for all the models and comparison forms tested, achieving an average relative improvement of 47.46%. Remarkably, PORTIA enables less advanced GPT models to achieve 88% agreement with the state-of-the-art GPT-4 model at just 10% of the cost. Furthermore, it rectifies around 80% of the position bias instances within the GPT-4 model, elevating its consistency rate up to 98%. Subsequent human evaluations indicate that the PORTIA-enhanced GPT-3.5 model can even surpass the standalone GPT-4 in terms of alignment with human evaluators. These findings highlight PORTIA's ability to correct position bias, improve LLM consistency, and boost performance while keeping cost-efficiency. This represents a valuable step toward a more reliable and scalable use of LLMs for automated evaluations across diverse applications.

Software plays a crucial role in our daily lives, and therefore the quality and security of software systems have become increasingly important. However, vulnerabilities in software still pose a significant threat, as they can have serious consequences. Recent advances in automated program repair have sought to automatically detect and fix bugs using data-driven techniques. Sophisticated deep learning methods have been applied to this area and have achieved promising results. However, existing benchmarks for training and evaluating these techniques remain limited, as they tend to focus on a single programming language and have relatively small datasets. Moreover, many benchmarks tend to be outdated and lack diversity, focusing on a specific codebase. Worse still, the quality of bug explanations in existing datasets is low, as they typically use imprecise and uninformative commit messages as explanations. To address these issues, we propose an automated collecting framework REEF to collect REal-world vulnErabilities and Fixes from open-source repositories. We develop a multi-language crawler to collect vulnerabilities and their fixes, and design metrics to filter for high-quality vulnerability-fix pairs. Furthermore, we propose a neural language model-based approach to generate high-quality vulnerability explanations, which is key to producing informative fix messages. Through extensive experiments, we demonstrate that our approach can collect high-quality vulnerability-fix pairs and generate strong explanations. The dataset we collect contains 4,466 CVEs with 30,987 patches (including 236 CWE) across 7 programming languages with detailed related information, which is superior to existing benchmarks in scale, coverage, and quality. Evaluations by human experts further confirm that our framework produces high-quality vulnerability explanations., Comment: Accepted by ASE 2023 Industry Challenge(Competition) Track

Automated code vulnerability detection has gained increasing attention in recent years. The deep learning (DL)-based methods, which implicitly learn vulnerable code patterns, have proven effective in vulnerability detection. The performance of DL-based methods usually relies on the quantity and quality of labeled data. However, the current labeled data are generally automatically collected, such as crawled from human-generated commits, making it hard to ensure the quality of the labels. Prior studies have demonstrated that the non-vulnerable code (i.e., negative labels) tends to be unreliable in commonly-used datasets, while vulnerable code (i.e., positive labels) is more determined. Considering the large numbers of unlabeled data in practice, it is necessary and worth exploring to leverage the positive data and large numbers of unlabeled data for more accurate vulnerability detection. In this paper, we focus on the Positive and Unlabeled (PU) learning problem for vulnerability detection and propose a novel model named PILOT, i.e., PositIve and unlabeled Learning mOdel for vulnerability deTection. PILOT only learns from positive and unlabeled data for vulnerability detection. It mainly contains two modules: (1) A distance-aware label selection module, aiming at generating pseudo-labels for selected unlabeled data, which involves the inter-class distance prototype and progressive fine-tuning; (2) A mixed-supervision representation learning module to further alleviate the influence of noise and enhance the discrimination of representations., Comment: This paper is accepted by ASE 2023

Virtual Reality (VR) technology has become increasingly popular in recent years as a key enabler of the Metaverse. VR applications have unique characteristics, including the revolutionized human-computer interaction mechanisms, that distinguish them from traditional software. Hence, user expectations for the software quality of VR applications diverge from those for traditional software. Investigating these quality expectations is crucial for the effective development and maintenance of VR applications, which remains an under-explored area in prior research. To bridge the gap, we conduct the first large-scale empirical study to model the software quality of VR applications from users' perspectives. To this end, we analyze 1,132,056 user reviews of 14,150 VR applications across seven app stores through a semiautomatic review mining approach. We construct a taxonomy of 12 software quality attributes that are of major concern to VR users. Our analysis reveals that the VR-specific quality attributes are of utmost importance to users, which are closely related to the most unique properties of VR applications like revolutionized interaction mechanisms and immersive experiences. Our examination of relevant user complaints reveals the major factors impacting user satisfaction with VR-specific quality attributes. We identify that poor design or implementation of the movement mechanisms, control mechanisms, multimedia systems, and physics, can significantly degrade the user experience. Moreover, we discuss the implications of VR quality assurance for both developers and researchers to shed light on future work. For instance, we suggest developers implement sufficient accessibility and comfort options for users with mobility limitations, sensory impairments, and other specific needs to customize the interaction mechanisms. Our datasets and results will be released to facilitate follow-up studies.

Python is a popular dynamic programming language, evidenced by its ranking as the second most commonly used language on GitHub. However, its dynamic type system can lead to potential type errors, leading researchers to explore automatic type inference approaches for Python programs. The rule-based type inference approaches can ensure the accuracy of predicted variable types, but they suffer from low coverage problems. Supervised type inference approaches, while feature-agnostic, require large, high-quality annotated datasets and are limited to pre-defined types. As zero-shot approaches, the cloze-style approaches reformulate the type inference problem into a fill-in-the-blank problem. However, their performance is limited. This paper introduces TypeGen, a few-shot generative type inference approach that incorporates static domain knowledge from static analysis. TypeGen creates chain-of-thought (COT) prompts by translating the type inference steps of static analysis into prompts based on the type dependency graphs (TDGs), enabling language models to learn from how static analysis infers types. By combining COT prompts with code slices and type hints, TypeGen constructs example prompts from human annotations. TypeGen only requires very few annotated examples to teach language models to generate similar COT prompts via in-context learning. Moreover, TypeGen enhances the interpretability of results through the use of the input-explanation-output strategy. Experiments show that TypeGen outperforms the best baseline Type4Py by 10.0% for argument type prediction and 22.5% in return value type prediction in terms of top-1 Exact Match by using only five examples. Furthermore, TypeGen achieves substantial improvements of 27% to 84% compared to the zero-shot performance of large language models with parameter sizes ranging from 1.3B to 175B in terms of top-1 Exact Match., Comment: This paper has been accepted by ASE'23

Prior studies generally focus on software vulnerability detection and have demonstrated the effectiveness of Graph Neural Network (GNN)-based approaches for the task. Considering the various types of software vulnerabilities and the associated different degrees of severity, it is also beneficial to determine the type of each vulnerable code for developers. In this paper, we observe that the distribution of vulnerability type is long-tailed in practice, where a small portion of classes have massive samples (i.e., head classes) but the others contain only a few samples (i.e., tail classes). Directly adopting previous vulnerability detection approaches tends to result in poor detection performance, mainly due to two reasons. First, it is difficult to effectively learn the vulnerability representation due to the over-smoothing issue of GNNs. Second, vulnerability types in tails are hard to be predicted due to the extremely few associated samples.To alleviate these issues, we propose a Long-taIled software VulnerABiLity typE classification approach, called LIVABLE. LIVABLE mainly consists of two modules, including (1) vulnerability representation learning module, which improves the propagation steps in GNN to distinguish node representations by a differentiated propagation method. A sequence-to-sequence model is also involved to enhance the vulnerability representations. (2) adaptive re-weighting module, which adjusts the learning weights for different types according to the training epochs and numbers of associated samples by a novel training loss.

Although the dynamic type system of Python facilitates the developers in writing Python programs, it also brings type errors at run-time. There exist rule-based approaches for automatically repairing Python type errors. The approaches can generate accurate patches but they require domain experts to design patch synthesis rules and suffer from low template coverage of real-world type errors. Learning-based approaches alleviate the manual efforts in designing patch synthesis rules. Among the learning-based approaches, the prompt-based approach which leverages the knowledge base of code pre-trained models via pre-defined prompts, obtains state-of-the-art performance in general program repair tasks. However, such prompts are manually defined and do not involve any specific clues for repairing Python type errors, resulting in limited effectiveness. How to automatically improve prompts with the domain knowledge for type error repair is challenging yet under-explored. In this paper, we present TypeFix, a novel prompt-based approach with fix templates incorporated for repairing Python type errors. TypeFix first mines generalized fix templates via a novel hierarchical clustering algorithm. The identified fix templates indicate the common edit patterns and contexts of existing type error fixes. TypeFix then generates code prompts for code pre-trained models by employing the generalized fix templates as domain knowledge, in which the masks are adaptively located for each type error instead of being pre-determined. Experiments on two benchmarks, including BugsInPy and TypeBugs, show that TypeFix successfully repairs 26 and 55 type errors, outperforming the best baseline approach by 9 and 14, respectively. Besides, the proposed fix template mining approach can cover 75% of developers' patches in both benchmarks, increasing the best rule-based approach PyTER by more than 30%., Comment: This paper has been accepted by ICSE'24

With the development of deep learning (DL), DL-based code search models have achieved state-of-the-art performance and have been widely used by developers during software development. However, the security issue, e.g., recommending vulnerable code, has not received sufficient attention, which will bring potential harm to software development. Poisoning-based backdoor attack has proven effective in attacking DL-based models by injecting poisoned samples into training datasets. However, previous work shows that the attack technique does not perform successfully on all DL-based code search models and tends to fail for Transformer-based models, especially pretrained models. Besides, the infected models generally perform worse than benign models, which makes the attack not stealthy enough and thereby hinders the adoption by developers. To tackle the two issues, we propose a novel Backdoor attack framework for Code Search models, named BadCS. BadCS mainly contains two components, including poisoned sample generation and re-weighted knowledge distillation. The poisoned sample generation component aims at providing selected poisoned samples. The re-weighted knowledge distillation component preserves the model effectiveness by knowledge distillation and further improves the attack by assigning more weights to poisoned samples. Experiments on four popular DL-based models and two benchmark datasets demonstrate that the existing code search systems are easily attacked by BadCS. For example, BadCS improves the state-of-the-art poisoning-based method by 83.03%-99.98% and 75.98%-99.90% on Python and Java datasets, respectively. Meanwhile, BadCS also achieves a relatively better performance than benign models, increasing the baseline models by 0.49% and 0.46% on average, respectively.

Pre-trained models of source code have gained widespread popularity in many code intelligence tasks. Recently, with the scaling of the model and corpus size, large language models have shown the ability of in-context learning (ICL). ICL employs task instructions and a few examples as demonstrations, and then inputs the demonstrations to the language models for making predictions. This new learning paradigm is training-free and has shown impressive performance in various natural language processing and code intelligence tasks. However, the performance of ICL heavily relies on the quality of demonstrations, e.g., the selected examples. It is important to systematically investigate how to construct a good demonstration for code-related tasks. In this paper, we empirically explore the impact of three key factors on the performance of ICL in code intelligence tasks: the selection, order, and number of demonstration examples. We conduct extensive experiments on three code intelligence tasks including code summarization, bug fixing, and program synthesis. Our experimental results demonstrate that all the above three factors dramatically impact the performance of ICL in code intelligence tasks. Additionally, we summarize our findings and provide takeaway suggestions on how to construct effective demonstrations, taking into account these three perspectives. We also show that a carefully-designed demonstration based on our findings can lead to substantial improvements over widely-used demonstration construction methods, e.g., improving BLEU-4, EM, and EM by at least 9.90%, 175.96%, and 50.81% on code summarization, bug fixing, and program synthesis, respectively, Comment: This paper is accepted by ASE 2023

Recent advances in large language models (LLMs) significantly boost their usage in software engineering. However, training a well-performing LLM demands a substantial workforce for data collection and annotation. Moreover, training datasets may be proprietary or partially open, and the process often requires a costly GPU cluster. The intellectual property value of commercial LLMs makes them attractive targets for imitation attacks, but creating an imitation model with comparable parameters still incurs high costs. This motivates us to explore a practical and novel direction: slicing commercial black-box LLMs using medium-sized backbone models. In this paper, we explore the feasibility of launching imitation attacks on LLMs to extract their specialized code abilities, such as"code synthesis" and "code translation." We systematically investigate the effectiveness of launching code ability extraction attacks under different code-related tasks with multiple query schemes, including zero-shot, in-context, and Chain-of-Thought. We also design response checks to refine the outputs, leading to an effective imitation training process. Our results show promising outcomes, demonstrating that with a reasonable number of queries, attackers can train a medium-sized backbone model to replicate specialized code behaviors similar to the target LLMs. We summarize our findings and insights to help researchers better understand the threats posed by imitation attacks, including revealing a practical attack surface for generating adversarial code examples against LLMs., Comment: 13 pages

This paper focuses on Code Generation task that aims at generating relevant code fragments according to given natural language descriptions. In the process of software development, developers often encounter two scenarios. One is requested to write a large amount of repetitive and low-technical code for implementing common functionalities. The other is writing code that depends on specific task requirements, which may necessitate the use of external resources such as documentation or other tools. Therefore, code generation has received a lot of attention among academia and industry for assisting developers in coding. In fact, it has also been one of the key concerns in the field of software engineering to make machines understand users' requirements and write programs on their own. The recent development of deep learning techniques especially pre-training models make the code generation task achieve promising performance. In this paper, we systematically review the current work on deep learning-based code generation and classify the current deep learning-based code generation methods into three categories: methods based on code features, methods incorporated with retrieval, and methods incorporated with post-processing. The first category refers to the methods that use deep learning algorithms for code generation based on code features, and the second and third categories of methods improve the performance of the methods in the first category. In this paper, the existing research results of each category of methods are systematically reviewed, summarized and commented. Besides, the paper summarizes and analyzes the corpus and the popular evaluation metrics used in the existing code generation work. Finally, the paper summarizes the overall literature review and provides a prospect on future research directions worthy of attention., Comment: in Chinese language

Prior studies have demonstrated the effectiveness of Deep Learning (DL) in automated software vulnerability detection. Graph Neural Networks (GNNs) have proven effective in learning the graph representations of source code and are commonly adopted by existing DL-based vulnerability detection methods. However, the existing methods are still limited by the fact that GNNs are essentially difficult to handle the connections between long-distance nodes in a code structure graph. Besides, they do not well exploit the multiple types of edges in a code structure graph (such as edges representing data flow and control flow). Consequently, despite achieving state-of-the-art performance, the existing GNN-based methods tend to fail to capture global information (i.e., long-range dependencies among nodes) of code graphs. To mitigate these issues, in this paper, we propose a novel vulnerability detection framework with grAph siMplification and enhanced graph rePresentation LEarning, named AMPLE. AMPLE mainly contains two parts: 1) graph simplification, which aims at reducing the distances between nodes by shrinking the node sizes of code structure graphs; 2) enhanced graph representation learning, which involves one edge-aware graph convolutional network module for fusing heterogeneous edge information into node representations and one kernel-scaled representation module for well capturing the relations between distant graph nodes. Experiments on three public benchmark datasets show that AMPLE outperforms the state-of-the-art methods by 0.39%-35.32% and 7.64%-199.81% with respect to the accuracy and F1 score metrics, respectively. The results demonstrate the effectiveness of AMPLE in learning global information of code graphs for vulnerability detection., Comment: 13 pages, 8 figures, Accepted for publication in the ICSE 23 Technical Track

Previous research on code intelligence usually trains a deep learning model on a fixed dataset in an offline manner. However, in real-world scenarios, new code repositories emerge incessantly, and the carried new knowledge is beneficial for providing up-to-date code intelligence services to developers. In this paper, we aim at the following problem: How to enable code intelligence models to continually learn from ever-increasing data? One major challenge here is catastrophic forgetting, meaning that the model can easily forget knowledge learned from previous datasets when learning from the new dataset. To tackle this challenge, we propose REPEAT, a novel method for continual learning of code intelligence models. Specifically, REPEAT addresses the catastrophic forgetting problem with representative exemplars replay and adaptive parameter regularization. The representative exemplars replay component selects informative and diverse exemplars in each dataset and uses them to retrain model periodically. The adaptive parameter regularization component recognizes important parameters in the model and adaptively penalizes their changes to preserve the knowledge learned before. We evaluate the proposed approach on three code intelligence tasks including code summarization, software vulnerability detection, and code clone detection. Extensive experiments demonstrate that REPEAT consistently outperforms baseline methods on all tasks. For example, REPEAT improves the conventional fine-tuning method by 1.22, 5.61, and 1.72 on code summarization, vulnerability detection and clone detection, respectively., Comment: Accepted to ICSE'2023

Code completion has become a common practice for programmers during their daily programming activities. It aims at automatically predicting the next tokens or lines that the programmers tend to use. A good code completion tool can substantially save keystrokes and improve the programming efficiency for programmers. Recently, various techniques for code completion have been proposed for usage in practice. However, it is still unclear what are practitioners' expectations on code completion and whether existing research has met their demands. To fill the gap, we perform an empirical study by first interviewing 15 practitioners and then surveying 599 practitioners from 18 IT companies about their expectations on code completion. We then compare the practitioners' demands with current research via conducting a literature review of papers on code completion published in premier publication venues from 2012 to 2022. Based on the comparison, we highlight the directions desirable for researchers to invest efforts towards developing code completion techniques for meeting practitioners' expectations., Comment: 12 pages

In recent years, deep learning (DL)-based methods have been widely used in code vulnerability detection. The DL-based methods typically extract structural information from source code, e.g., code structure graph, and adopt neural networks such as Graph Neural Networks (GNNs) to learn the graph representations. However, these methods fail to consider the heterogeneous relations in the code structure graph, i.e., the heterogeneous relations mean that the different types of edges connect different types of nodes in the graph, which may obstruct the graph representation learning. Besides, these methods are limited in capturing long-range dependencies due to the deep levels in the code structure graph. In this paper, we propose a Meta-path based Attentional Graph learning model for code vulNErability deTection, called MAGNET. MAGNET constructs a multi-granularity meta-path graph for each code snippet, in which the heterogeneous relations are denoted as meta-paths to represent the structural information. A meta-path based hierarchical attentional graph neural network is also proposed to capture the relations between distant nodes in the graph. We evaluate MAGNET on three public datasets and the results show that MAGNET outperforms the best baseline method in terms of F1 score by 6.32%, 21.50%, and 25.40%, respectively. MAGNET also achieves the best performance among all the baseline methods in detecting Top-25 most dangerous Common Weakness Enumerations (CWEs), further demonstrating its effectiveness in vulnerability detection., Comment: Accepted by TSE

Code completion is a valuable topic in both academia and industry. Recently, large-scale mono-programming-lingual (MonoPL) pre-training models have been proposed to boost the performance of code completion. However, the code completion on low-resource programming languages (PL) is difficult for the data-driven paradigm, while there are plenty of developers using low-resource PLs. On the other hand, there are few studies exploring the effects of multi-programming-lingual (MultiPL) pre-training for the code completion, especially the impact on low-resource programming languages. To this end, we propose the MultiCoder to enhance the low-resource code completion via MultiPL pre-training and MultiPL Mixture-of-Experts (MoE) layers. We further propose a novel PL-level MoE routing strategy (PL-MoE) for improving the code completion on all PLs. Experimental results on CodeXGLUE and MultiCC demonstrate that 1) the proposed MultiCoder significantly outperforms the MonoPL baselines on low-resource programming languages, and 2) the PL-MoE module further boosts the performance on six programming languages. In addition, we analyze the effects of the proposed method in details and explore the effectiveness of our method in a variety of scenarios.

Natural language processing for programming aims to use NLP techniques to assist programming. It is increasingly prevalent for its effectiveness in improving productivity. Distinct from natural language, a programming language is highly structured and functional. Constructing a structure-based representation and a functionality-oriented algorithm is at the heart of program understanding and generation. In this paper, we conduct a systematic review covering tasks, datasets, evaluation methods, techniques, and models from the perspective of the structure-based and functionality-oriented property, aiming to understand the role of the two properties in each component. Based on the analysis, we illustrate unexplored areas and suggest potential directions for future work.

Aspect-based sentiment analysis (ABSA) aims at extracting opinionated aspect terms in review texts and determining their sentiment polarities, which is widely studied in both academia and industry. As a fine-grained classification task, the annotation cost is extremely high. Domain adaptation is a popular solution to alleviate the data deficiency issue in new domains by transferring common knowledge across domains. Most cross-domain ABSA studies are based on structure correspondence learning (SCL), and use pivot features to construct auxiliary tasks for narrowing down the gap between domains. However, their pivot-based auxiliary tasks can only transfer knowledge of aspect terms but not sentiment, limiting the performance of existing models. In this work, we propose a novel Syntax-guided Domain Adaptation Model, named SDAM, for more effective cross-domain ABSA. SDAM exploits syntactic structure similarities for building pseudo training instances, during which aspect terms of target domain are explicitly related to sentiment polarities. Besides, we propose a syntax-based BERT mask language model for further capturing domain-invariant features. Finally, to alleviate the sentiment inconsistency issue in multi-gram aspect terms, we introduce a span-based joint aspect term and sentiment analysis module into the cross-domain End2End ABSA. Experiments on five benchmark datasets show that our model consistently outperforms the state-of-the-art baselines with respect to Micro-F1 metric for the cross-domain End2End ABSA task., Comment: I want to withdraw this article due to personal reason

App reviews are crowdsourcing knowledge of user experience with the apps, providing valuable information for app release planning, such as major bugs to fix and important features to add. There exist prior explorations on app review mining for release planning, however, most of the studies strongly rely on pre-defined classes or manually-annotated reviews. Also, the new review characteristic, i.e., the number of users who rated the review as helpful, which can help capture important reviews, has not been considered previously. In the paper, we propose a novel framework, named SOLAR, aiming at accurately summarizing helpful user reviews to developers. The framework mainly contains three modules: The review helpfulness prediction module, topic-sentiment modeling module, and multi-factor ranking module. The review helpfulness prediction module assesses the helpfulness of reviews, i.e., whether the review is useful for developers. The topic-sentiment modeling module groups the topics of the helpful reviews and also predicts the associated sentiment, and the multi-factor ranking module aims at prioritizing semantically representative reviews for each topic as the review summary. Experiments on five popular apps indicate that SOLAR is effective for review summarization and promising for facilitating app release planning.

Transformer-based models have achieved great success on sentence pair modeling tasks, such as answer selection and natural language inference (NLI). These models generally perform cross-attention over input pairs, leading to prohibitive computational costs. Recent studies propose dual-encoder and late interaction architectures for faster computation. However, the balance between the expressive of cross-attention and computation speedup still needs better coordinated. To this end, this paper introduces a novel paradigm MixEncoder for efficient sentence pair modeling. MixEncoder involves a light-weight cross-attention mechanism. It conducts query encoding only once while modeling the query-candidate interaction in parallel. Extensive experiments conducted on four tasks demonstrate that our MixEncoder can speed up sentence pairing by over 113x while achieving comparable performance as the more expensive cross-attention models., Comment: Accepted to EMNLP 2023

Incorporating knowledge graphs (KGs) as side information in recommendation has recently attracted considerable attention. Despite the success in general recommendation scenarios, prior methods may fall short of performance satisfaction for the cold-start problem in which users are associated with very limited interactive information. Since the conventional methods rely on exploring the interaction topology, they may however fail to capture sufficient information in cold-start scenarios. To mitigate the problem, we propose a novel Knowledge-aware Neural Networks with Personalized Feature Referencing Mechanism, namely KPER. Different from most prior methods which simply enrich the targets' semantics from KGs, e.g., product attributes, KPER utilizes the KGs as a "semantic bridge" to extract feature references for cold-start users or items. Specifically, given cold-start targets, KPER first probes semantically relevant but not necessarily structurally close users or items as adaptive seeds for referencing features. Then a Gated Information Aggregation module is introduced to learn the combinatorial latent features for cold-start users and items. Our extensive experiments over four real-world datasets show that, KPER consistently outperforms all competing methods in cold-start scenarios, whilst maintaining superiority in general scenarios without compromising overall performance, e.g., by achieving 0.81%-16.08% and 1.01%-14.49% performance improvement across all datasets in Top-10 recommendation., Comment: under submission

Mobile apps are becoming an integral part of people's daily life by providing various functionalities, such as messaging and gaming. App developers try their best to ensure user experience during app development and maintenance to improve the rating of their apps on app platforms and attract more user downloads. Previous studies indicated that responding to users' reviews tends to change their attitude towards the apps positively. Users who have been replied are more likely to update the given ratings. However, reading and responding to every user review is not an easy task for developers since it is common for popular apps to receive tons of reviews every day. Thus, automation tools for review replying are needed. To address the need above, the paper introduces a Transformer-based approach, named TRRGen, to automatically generate responses to given user reviews. TRRGen extracts apps' categories, rating, and review text as the input features. By adapting a Transformer-based model, TRRGen can generate appropriate replies for new reviews. Comprehensive experiments and analysis on the real-world datasets indicate that the proposed approach can generate high-quality replies for users' reviews and significantly outperform current state-of-art approaches on the task. The manual validation results on the generated replies further demonstrate the effectiveness of the proposed approach., Comment: Accepted to Software: Practice and Experience (SPE)