The utilization of programming language (PL) models, pre-trained on large-scale code corpora, as a means of automating software engineering processes has demonstrated considerable potential in streamlining various code generation tasks such as code completion, code translation, and program synthesis. However, current approaches mainly rely on supervised fine-tuning objectives borrowed from text generation, neglecting unique sequence-level characteristics of code, including but not limited to compilability as well as syntactic and functional correctness. To address this limitation, we propose PPOCoder, a new framework for code generation that synergistically combines pre-trained PL models with Proximal Policy Optimization (PPO) which is a widely used deep reinforcement learning technique. By utilizing non-differentiable feedback from code execution and structure alignment, PPOCoder seamlessly integrates external code-specific knowledge into the model optimization process. It's important to note that PPOCoder is a task-agnostic and model-agnostic framework that can be used across different code generation tasks and PLs. Extensive experiments on three code generation tasks demonstrate the effectiveness of our proposed approach compared to SOTA methods, achieving significant improvements in compilation success rates and functional correctness across different PLs.
相關內容
The Function-as-a-service (FaaS) computing model has recently seen significant growth especially for highly scalable, event-driven applications. The easy-to-deploy and cost-efficient fine-grained billing of FaaS is highly attractive to big data applications. However, the stateless nature of serverless platforms poses major challenges when supporting stateful I/O intensive workloads such as a lack of native support for stateful execution, state sharing, and inter-function communication. In this paper, we explore the feasibility of performing stateful big data analytics on serverless platforms and improving I/O throughput of functions by using modern storage technologies such as Intel Optane DC Persistent Memory (PMEM). To this end, we propose Marvel, an end-to-end architecture built on top of the popular serverless platform, Apache OpenWhisk and Apache Hadoop. Marvel makes two main contributions: (1) enable stateful function execution on OpenWhisk by maintaining state information in an in-memory caching layer; and (2) provide access to PMEM backed HDFS storage for faster I/O performance. Our evaluation shows that Marvel reduces the overall execution time of big data applications by up to 86.6% compared to current MapReduce implementations on AWS Lambda.
Graded type systems, such as the one underlying the Granule programming language, allow various different properties of a program's behaviour to be tracked via annotating types with additional information, which we call grades. One example of such a property, often used as a case study in prior work on graded types, is information flow control, in which types are graded by a lattice of security levels allowing noninterference properties to be automatically verified and enforced. These typically focus on one particular aspect of security, however, known as confidentiality; public outputs are prohibited from depending on private inputs. Integrity, a property specifying that trusted outputs must not depend on untrusted inputs, has not been examined in this context. This short paper aims to remedy this omission. It is well-known that confidentiality and integrity are in some sense dual properties, but simply reversing the ordering of the security lattice turns out to be unsatisfactory for the purpose of combining both kinds of property in a single system, at least in our setting. We analogize the situation to recent work on embedding both linear and uniqueness types in a graded framework, and use this framing to demonstrate that we can enforce both integrity and confidentiality alongside one another. The main idea is to add an additional flavour of modality annotated for integrity, such that the existing graded comonad for tracking confidentiality now also acts as a relative monad over the new modality, with rules allowing information to flow from trusted to public to private.
We present a framework for sandboxing and restricting features of the OCaml programming language to effectively automate the grading of programming exercises, scaling to hundreds of submissions. We describe how to disable language and library features that should not be used to solve a given exercise. We present an overview of an implementation of a mock IO system to allow testing of IO-related exercises in a controlled environment. Finally, we detail a number of security considerations to ensure submitted code remains sandboxed, allowing automatic grading to be trusted without manual verification. The source code of our implementation is publicly available.
For decades, much software engineering research has been dedicated to devising automated solutions aimed at enhancing developer productivity and elevating software quality. The past two decades have witnessed an unparalleled surge in the development of intelligent solutions tailored for software engineering tasks. This momentum established the Artificial Intelligence for Software Engineering (AI4SE) area, which has swiftly become one of the most active and popular areas within the software engineering field. This Future of Software Engineering (FoSE) paper navigates through several focal points. It commences with a succinct introduction and history of AI4SE. Thereafter, it underscores the core challenges inherent to AI4SE, particularly highlighting the need to realize trustworthy and synergistic AI4SE. Progressing, the paper paints a vision for the potential leaps achievable if AI4SE's key challenges are surmounted, suggesting a transition towards Software Engineering 2.0. Two strategic roadmaps are then laid out: one centered on realizing trustworthy AI4SE, and the other on fostering synergistic AI4SE. While this paper may not serve as a conclusive guide, its intent is to catalyze further progress. The ultimate aspiration is to position AI4SE as a linchpin in redefining the horizons of software engineering, propelling us toward Software Engineering 2.0.
We propose employing a debiased-regularized, high-dimensional generalized method of moments (GMM) framework to perform inference on large-scale spatial panel networks. In particular, network structure with a flexible sparse deviation, which can be regarded either as latent or as misspecified from a predetermined adjacency matrix, is estimated using debiased machine learning approach. The theoretical analysis establishes the consistency and asymptotic normality of our proposed estimator, taking into account general temporal and spatial dependency inherent in the data-generating processes. The dimensionality allowance in presence of dependency is discussed. A primary contribution of our study is the development of uniform inference theory that enables hypothesis testing on the parameters of interest, including zero or non-zero elements in the network structure. Additionally, the asymptotic properties for the estimator are derived for both linear and nonlinear moments. Simulations demonstrate superior performance of our proposed approach. Lastly, we apply our methodology to investigate the spatial network effect of stock returns.
Search-based software testing (SBST) typically relies on fitness functions to guide the search exploration toward software failures. There are two main techniques to define fitness functions: (a) automated fitness function computation from the specification of the system requirements, and (b) manual fitness function design. Both techniques have advantages. The former uses information from the system requirements to guide the search toward portions of the input domain more likely to contain failures. The latter uses the engineers' domain knowledge. We propose ATheNA, a novel SBST framework that combines fitness functions automatically generated from requirements specifications and those manually defined by engineers. We design and implement ATheNA-S, an instance of ATheNA that targets Simulink models. We evaluate ATheNA-S by considering a large set of models from different domains. Our results show that ATheNA-S generates more failure-revealing test cases than existing baseline tools and that the difference between the runtime performance of ATheNA-S and the baseline tools is not statistically significant. We also assess whether ATheNA-S could generate failure-revealing test cases when applied to two representative case studies: one from the automotive domain and one from the medical domain. Our results show that ATheNA-S successfully revealed a requirement violation in our case studies.
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.
For traditional modular software systems, "high cohesion, low coupling" is a recommended setting while it remains so for microservice architectures. However, coupling phenomena commonly exist therein which are caused by cross-service calls and dependencies. In addition, it is noticeable that teams for microservice projects can also suffer from high coupling issues in terms of their cross-service contribution, which can inevitably result in technical debt and high managerial costs. Such organizational coupling needs to be detected and mitigated in time to prevent future losses. Therefore, this paper proposes an automatable approach to evaluate the organizational couple by investigating the microservice ownership and cross-service contribution.
Few-shot learning (FSL) methods typically assume clean support sets with accurately labeled samples when training on novel classes. This assumption can often be unrealistic: support sets, no matter how small, can still include mislabeled samples. Robustness to label noise is therefore essential for FSL methods to be practical, but this problem surprisingly remains largely unexplored. To address mislabeled samples in FSL settings, we make several technical contributions. (1) We offer simple, yet effective, feature aggregation methods, improving the prototypes used by ProtoNet, a popular FSL technique. (2) We describe a novel Transformer model for Noisy Few-Shot Learning (TraNFS). TraNFS leverages a transformer's attention mechanism to weigh mislabeled versus correct samples. (3) Finally, we extensively test these methods on noisy versions of MiniImageNet and TieredImageNet. Our results show that TraNFS is on-par with leading FSL methods on clean support sets, yet outperforms them, by far, in the presence of label noise.
Existing methods for vision-and-language learning typically require designing task-specific architectures and objectives for each task. For example, a multi-label answer classifier for visual question answering, a region scorer for referring expression comprehension, and a language decoder for image captioning, etc. To alleviate these hassles, in this work, we propose a unified framework that learns different tasks in a single architecture with the same language modeling objective, i.e., multimodal conditional text generation, where our models learn to generate labels in text based on the visual and textual inputs. On 7 popular vision-and-language benchmarks, including visual question answering, referring expression comprehension, visual commonsense reasoning, most of which have been previously modeled as discriminative tasks, our generative approach (with a single unified architecture) reaches comparable performance to recent task-specific state-of-the-art vision-and-language models. Moreover, our generative approach shows better generalization ability on answering questions that have rare answers. In addition, we show that our framework allows multi-task learning in a single architecture with a single set of parameters, which achieves similar performance to separately optimized single-task models. Our code will be publicly available at: //github.com/j-min/VL-T5
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191