Developers often perform repetitive code editing activities for various reasons (e.g., code refactoring) during software development. Pre-trained code editing models have achieved the state-of-the-art (SOTA) results. Pre-trained models are first pre-trained with pre-training tasks and fine-tuned with the code editing task. Existing pre-training tasks mainly are code infilling tasks (e.g., masked language modeling), which are derived from the natural language processing field and are not designed for automatic code editing. This paper proposes a novel pre-training task specialized in code editing and presents an effective pre-trained code editing model named CodeEditor. Our pre-training task further improves the performance and generalization ability of code editing models. Specifically, we collect lots of real-world code snippets as the ground truth and use a powerful generator to rewrite them into mutated versions. Then, we pre-train our CodeEditor to edit mutated versions into the corresponding ground truth, to learn edit patterns. We conduct experiments on four code editing datasets and evaluate the pre-trained CodeEditor in three settings. (1) In the fine-tuning setting, we train the pre-trained CodeEditor with four datasets and evaluate it on the test data. CodeEditor outperforms the SOTA baselines by 15%, 25.5%, and 9.4% and 26.6% on four datasets. (2) In the few-shot setting, we train the pre-trained CodeEditor with limited data and evaluate it on the test data. CodeEditor substantially performs better than all baselines. (3) In the zero-shot setting, CodeEditor correctly edits 1,113 programs while the SOTA baselines can not work.
相關內容
Bug-fix benchmarks are fundamental in advancing various sub-fields of software engineering such as automatic program repair (APR) and fault localization (FL). A good benchmark must include recent examples that accurately reflect technologies and development practices of today. To be executable in the long term, a benchmark must feature test suites that do not degrade overtime due to, for example, dependencies that are no longer available. Existing benchmarks fail in meeting both criteria. For instance, Defects4J, one of the foremost Java benchmarks, last received an update in 2020. Moreover, full-reproducibility has been neglected by the majority of existing benchmarks. In this paper, we present GitBug-Actions: a novel tool for building bug-fix benchmarks with modern and fully-reproducible bug-fixes. GitBug-Actions relies on the most popular CI platform, GitHub Actions, to detect bug-fixes and smartly locally execute the CI pipeline in a controlled and reproducible environment. To the best of our knowledge, we are the first to rely on GitHub Actions to collect bug-fixes. To demonstrate our toolchain, we deploy GitBug-Actions to build a proof-of-concept Go bug-fix benchmark containing executable, fully-reproducible bug-fixes from different repositories. A video demonstrating GitBug-Actions is available at: //youtu.be/aBWwa1sJYBs.
This work introduces a novel task, location-aware visual question generation (LocaVQG), which aims to generate engaging questions from data relevant to a particular geographical location. Specifically, we represent such location-aware information with surrounding images and a GPS coordinate. To tackle this task, we present a dataset generation pipeline that leverages GPT-4 to produce diverse and sophisticated questions. Then, we aim to learn a lightweight model that can address the LocaVQG task and fit on an edge device, such as a mobile phone. To this end, we propose a method which can reliably generate engaging questions from location-aware information. Our proposed method outperforms baselines regarding human evaluation (e.g., engagement, grounding, coherence) and automatic evaluation metrics (e.g., BERTScore, ROUGE-2). Moreover, we conduct extensive ablation studies to justify our proposed techniques for both generating the dataset and solving the task.
Due to the limited availability of data, existing few-shot learning methods trained from scratch fail to achieve satisfactory performance. In contrast, large-scale pre-trained models such as CLIP demonstrate remarkable few-shot and zero-shot capabilities. To enhance the performance of pre-trained models for downstream tasks, fine-tuning the model on downstream data is frequently necessary. However, fine-tuning the pre-trained model leads to a decrease in its generalizability in the presence of distribution shift, while the limited number of samples in few-shot learning makes the model highly susceptible to overfitting. Consequently, existing methods for fine-tuning few-shot learning primarily focus on fine-tuning the model's classification head or introducing additional structure. In this paper, we introduce a fine-tuning approach termed Feature Discrimination Alignment (FD-Align). Our method aims to bolster the model's generalizability by preserving the consistency of spurious features across the fine-tuning process. Extensive experimental results validate the efficacy of our approach for both ID and OOD tasks. Once fine-tuned, the model can seamlessly integrate with existing methods, leading to performance improvements. Our code can be found in //github.com/skingorz/FD-Align.
Despite outstanding performance in many tasks, language models are notoriously inclined to make factual errors in tasks requiring arithmetic computation. We address this deficiency by creating Calc-X, a collection of datasets that demonstrates the appropriate use of a calculator in reasoning chains. Calc-X is suitable for teaching language models to offload computations to a symbolic system. We survey and unify several existing chain-of-thought datasets into a proposed format, resulting in a standard collection of over 300,000 samples requiring arithmetic reasoning. Finally, we use the new Calc-X collection to train open-source calculator-using models we call Calcformers and show that these models approximately double the accuracy of generating correct results compared to vanilla language model baselines. We make all Calc-X datasets, source code and Calcformers models publicly available.
Road user trajectory prediction in dynamic environments is a challenging but crucial task for various applications, such as autonomous driving. One of the main challenges in this domain is the multimodal nature of future trajectories stemming from the unknown yet diverse intentions of the agents. Diffusion models have shown to be very effective in capturing such stochasticity in prediction tasks. However, these models involve many computationally expensive denoising steps and sampling operations that make them a less desirable option for real-time safety-critical applications. To this end, we present a novel framework that leverages diffusion models for predicting future trajectories in a computationally efficient manner. To minimize the computational bottlenecks in iterative sampling, we employ an efficient sampling mechanism that allows us to maximize the number of sampled trajectories for improved accuracy while maintaining inference time in real time. Moreover, we propose a scoring mechanism to select the most plausible trajectories by assigning relative ranks. We show the effectiveness of our approach by conducting empirical evaluations on common pedestrian (UCY/ETH) and autonomous driving (nuScenes) benchmark datasets on which our model achieves state-of-the-art performance on several subsets and metrics.
The field of safe multi-agent reinforcement learning, despite its potential applications in various domains such as drone delivery and vehicle automation, remains relatively unexplored. Training agents to learn optimal policies that maximize rewards while considering specific constraints can be challenging, particularly in scenarios where having a central controller to coordinate the agents during the training process is not feasible. In this paper, we address the problem of multi-agent policy optimization in a decentralized setting, where agents communicate with their neighbors to maximize the sum of their cumulative rewards while also satisfying each agent's safety constraints. We consider both peak and average constraints. In this scenario, there is no central controller coordinating the agents and both the rewards and constraints are only known to each agent locally/privately. We formulate the problem as a decentralized constrained multi-agent Markov Decision Problem and propose a momentum-based decentralized policy gradient method, DePAint, to solve it. To the best of our knowledge, this is the first privacy-preserving fully decentralized multi-agent reinforcement learning algorithm that considers both peak and average constraints. We also provide theoretical analysis and empirical evaluation of our algorithm in various scenarios and compare its performance to centralized algorithms that consider similar constraints.
With the ever-increasing execution scale of high performance computing (HPC) applications, vast amounts of data are being produced by scientific research every day. Error-bounded lossy compression has been considered a very promising solution to address the big-data issue for scientific applications because it can significantly reduce the data volume with low time cost meanwhile allowing users to control the compression errors with a specified error bound. The existing error-bounded lossy compressors, however, are all developed based on inflexible designs or compression pipelines, which cannot adapt to diverse compression quality requirements/metrics favored by different application users. In this paper, we propose a novel dynamic quality metric oriented error-bounded lossy compression framework, namely QoZ. The detailed contribution is three-fold. (1) We design a novel highly-parameterized multi-level interpolation-based data predictor, which can significantly improve the overall compression quality with the same compressed size. (2) We design the error-bounded lossy compression framework QoZ based on the adaptive predictor, which can auto-tune the critical parameters and optimize the compression result according to user-specified quality metrics during online compression. (3) We evaluate QoZ carefully by comparing its compression quality with multiple state-of-the-arts on various real-world scientific application datasets. Experiments show that, compared with the second-best lossy compressor, QoZ can achieve up to 70% compression ratio improvement under the same error bound, up to 150% compression ratio improvement under the same PSNR, or up to 270% compression ratio improvement under the same SSIM.
Integrating third-party packages accelerates modern software engineering, but introduces the risk of software supply chain vulnerabilities. Vulnerabilities in applications' dependencies are being exploited worldwide. Often, these exploits leverage features that are present in a package, yet unneeded by an application. Unfortunately, the current generation of permission managers, such as SELinux, Docker containers, and the Java Security Manager, are too coarse-grained to usefully support engineers and operators in mitigating these vulnerabilities. Current approaches offer permissions only at the application's granularity, lumping legitimate operations made by safe packages with illegitimate operations made by exploited packages. This strategy does not reflect modern engineering practice. we need a permission manager capable of distinguishing between actions taken by different packages in an application's supply chain. In this paper, we describe Next-JSM, the first fine-grained ("supply chain aware") permission manager for Java applications. Next-JSM supports permission management at package-level granularity. Next-JSM faces three key challenges: operating on existing JVMs and without access to application or package source code, minimizing performance overhead in applications with many packages, and helping operators manage finer-grained permissions. We show that these challenges can be addressed through bytecode rewriting; appropriate data structures and algorithms; and an expressive permission notation plus automated tooling to establish default permission. In our evaluation, we report that Next-JSM mitigates 11 of the 12 package vulnerabilities we evaluated and incurs an average 2.72% overhead on the Dacapobench benchmark. Qualitatively, we argue that Next-JSM addresses the shortcomings of the (recently deprecated) Java Security Manager (JSM).
ChatGPT demonstrates significant potential to revolutionize software engineering (SE) by exhibiting outstanding performance in SE tasks such as code and document generation. However, the high reliability and risk control requirements in software engineering raise concerns about the lack of interpretability of ChatGPT. To address this concern, we conducted a study to evaluate the capabilities of ChatGPT and its limitations for code analysis in SE. We break down the abilities needed for artificial intelligence (AI) models to address SE tasks related to code analysis into three categories:1) syntax understanding, 2) static behavior understanding, and 3) dynamic behavior understanding. Our investigation focused on the ability of ChatGPT to comprehend code syntax and semantic structures, which include abstract syntax trees (AST), control flow graphs (CFG), and call graphs (CG). We assessed the performance of ChatGPT on cross-language tasks involving C, Java, Python, and Solidity. Our findings revealed that while ChatGPT has a talent for understanding code syntax, it struggles with comprehending code semantics, particularly dynamic semantics. We conclude that ChatGPT possesses capabilities similar to an Abstract Syntax Tree (AST) parser, demonstrating initial competencies in static code analysis. Furthermore, our study highlights that ChatGPT is susceptible to hallucinations when interpreting code semantic structures and fabricating nonexistent facts. These results indicate the need to explore methods to verify the correctness of ChatGPT output to ensure its dependability in SE. More importantly, our study provides an initial answer to why the codes generated by LLM are usually syntax correct but vulnerable.
Existing recommender systems extract the user preference based on learning the correlation in data, such as behavioral correlation in collaborative filtering, feature-feature, or feature-behavior correlation in click-through rate prediction. However, regretfully, the real world is driven by causality rather than correlation, and correlation does not imply causation. For example, the recommender systems can recommend a battery charger to a user after buying a phone, in which the latter can serve as the cause of the former, and such a causal relation cannot be reversed. Recently, to address it, researchers in recommender systems have begun to utilize causal inference to extract causality, enhancing the recommender system. In this survey, we comprehensively review the literature on causal inference-based recommendation. At first, we present the fundamental concepts of both recommendation and causal inference as the basis of later content. We raise the typical issues that the non-causality recommendation is faced. Afterward, we comprehensively review the existing work of causal inference-based recommendation, based on a taxonomy of what kind of problem causal inference addresses. Last, we discuss the open problems in this important research area, along with interesting future works.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191