Large language models (LLMs) have shown great success in code generation. LLMs take as the input a prompt and output the code. How to make prompts (i.e., Prompting Techniques) is a key question. Existing prompting techniques are designed for natural ...

Large language models (LLMs) provide round-the-clock personalized programming assistance, unlike course instructors or traditional online information sources such as Stack Overflow. While LLMs can aid in code generation, concerns about over-reliance and ...

Staged computation is a means to achieve maintainability and high performance simultaneously, by allowing a programmer to express domain-specific optimizations in a high-level programming language. Multi-stage programming languages such as MetaOCaml ...

Large language models (LLMs) are a new and powerful tool for a wide span of applications involving natural language and demonstrate impressive code generation abilities. The goal of this work is to automatically generate tests and use these tests ...

• LLMs enable basic test generation for compiler validation.
• Investigates suitable prompt engineering and fine-tuning techniques.
• The majority of passing tests are correct, while tests fail for a variety of reasons.

Data-parallel computations, such as linear algebra routines and stencil computations, constitute one of the most relevant classes in parallel computing, e.g., due to their importance for deep learning. Efficiently de-composing such computations for the ...

Although large language models (LLMs) have demonstrated remarkable code-generation ability, they still struggle with complex tasks. In real-world software development, humans usually tackle complex tasks through collaborative teamwork, a strategy that ...

The Isabelle proof assistant includes a small functional language, which allows users to write and reason about programs. So far, these programs could be extracted into a number of functional languages: Standard ML, OCaml, Scala, and Haskell. This ...

In this work, we consider the formal framework TOAST for timed asynchronous interactions featuring mixed-choice states. TOAST extends the theory of timed asynchronous session types to support modelling of communication protocols featuring timeouts, which ...

Code summary (CS) produces natural language descriptions based on code snippets, while code generation (CG) produces code snippets based on natural language. Since both tasks are intended to model the relationship between natural language and code ...

Transformers have revolutionized natural language processing (NLP) and have had a huge impact on automating tasks. Recently, transformers have led to the development of powerful large language models (LLMs), which have advanced automatic code ...

Code generation aims to map natural language descriptions to code snippets. Recent approaches using sequence-to-tree models have shown promising results. However, they generally adopt an autoregressive way to predict the next token based on ...

• Context-sensitive code generation technique.
• Design a novel sampling method for the bidirectional decoder.
• Evaluation on the real-world code generation datasets.

Runtime auto-remediation is crucial for ensuring the reliability and efficiency of distributed systems, especially within complex microservice-based applications. However, the complexity of modern microservice deployments often surpasses the capabilities ...

Tabular data is the most common format to publish and exchange structured data online. A clear example is the growing number of open data portals published by public administrations. However, exploitation of these data sources is currently limited to ...

This paper presents SeamlessMDD - our open-source framework for a gradual and effortless transition from traditional development to MDD (Model-Driven Development) that allows maintaining hand-written and generated code intertwined without the need ...

Modern automotive systems with adaptive control features require rigorous analysis to guarantee correct operation. We report our experience in modeling the automotive case study from the ABZ2020 conference using the ASMETA toolset, based on the ...

We propose MetaFM, a novel ML-style module system that enables users to decompose multi-stage programs (i.e., programs written in a typed multi-stage programming language) into loosely coupled components in a manner natural with respect to type ...$\mathbf{}\mathbf{}$$\mathbf{}\mathbf{}$${}^{}$$$

Retrieval-augmented code generation strengthens the generation model by using a retrieval model to select relevant code snippets from a code corpus. The synergy between retrieval and generation ensures that the generated code closely corresponds ...

• A Hierarchical Code Retrieval Mechanism for Efficiently Extracting Relevant Code Snippets from Extensive Code Repositories.
• An Intelligent Re-ranking Technique for Reassessing Retrieved Code Snippets According to Query Relevance.
• ...

Pre-trained code generation models (PCGMs) have been widely applied in neural code generation, which can generate executable code from functional descriptions in natural languages, possibly together with signatures. Despite substantial performance ...

The Security and Stability Control System (SSCS) is developed to ensure the safe and stable operation of power grids, effectively mitigating failure propagation through emergency control strategies. However, due to the diversity, complexity, and ...

Especially in industrial applications of formal modeling, validation is as important as verification. Thus, it is important to integrate the stakeholders’ and the domain experts’ feedback as early as possible. In this work, we propose two ...