相关论文: Can Program Synthesis be Used to Learn Merge Confl…

TeX is a widely-used typesetting system adopted by most publishers and professional societies. While TeX is responsible for generating a significant number of documents, irregularities in the TeX ecosystem may produce inconsistent…

Dealing with merge conflicts in version control systems is a challenging task for software developers. Resolving merge conflicts is a time-consuming and error-prone process, which distracts developers from important tasks. Recent work shows…

Synthesizing a program that realizes a logical specification is a classical problem in computer science. We examine a particular type of program synthesis, where the objective is to synthesize a strategy that reacts to a potentially…

We study the problem of synthesizing domain-specific languages (DSLs) for few-shot learning in symbolic domains. Given a base language and instances of few-shot learning problems, where each instance is split into training and testing…

Large language models (LLMs) often encounter knowledge conflicts, scenarios where discrepancy arises between the internal parametric knowledge of LLMs and non-parametric information provided in the prompt context. In this work we ask what…

We present MathDSL, a Domain-Specific Language (DSL) for mathematical equation solving, which, when deployed in program synthesis models, outperforms state-of-the-art reinforcement-learning-based methods. We also introduce a quantitative…

The rising popularity of Large Language Models (LLMs) has motivated exploring their use in code-related tasks. Code LLMs with more than millions of parameters are trained on a massive amount of code in different Programming Languages (PLs).…

Traditional multi-task learning architectures train a single model across multiple tasks through a shared encoder followed by task-specific decoders. Learning these models often requires specialized training algorithms that address…

Code completion is a prominent application of Large Language Models (LLMs) in software engineering. Due to the near real-time response requirements of this task, base models with small to medium-sized parameters are typically employed,…

The modern code review process is an integral part of the current software development practice. Considerable effort is given here to inspect code changes, find defects, suggest an improvement, and address the suggestions of the reviewers.…

LLMs demonstrate performance comparable to human abilities in complex tasks such as mathematical reasoning, but their robustness in mathematical reasoning under minor input perturbations still lacks systematic investigation. Existing…

Many program synthesis tasks prove too challenging for even state-of-the-art language models to solve in single attempts. Search-based evolutionary methods offer a promising alternative by exploring solution spaces iteratively, but their…

Large language models (LLMs) demonstrate impressive generalization abilities, yet adapting them effectively across multiple heterogeneous domains remains challenging due to inter-domain interference. To overcome this challenge, we propose a…

Fuzzing consists of repeatedly testing an application with modified, or fuzzed, inputs with the goal of finding security vulnerabilities in input-parsing code. In this paper, we show how to automate the generation of an input grammar…

Modern enterprise computing systems integrate numerous subsystems to resolve a common task by yielding emergent behavior. A widespread approach is using services implemented with Web technologies like REST or OpenAPI, which offer an…

Modern codebases evolve continuously: files are renamed or deleted; public APIs drift; behavior shifts within otherwise familiar modules. A model trained yesterday to map a developer's natural-language question to the exact set of…

A variant of the well-known Set Covering Problem is studied in this paper, where subsets of a collection have to be selected, and pairwise conflicts among subsets of items exist. The selection of each subset has a cost, and the inclusion of…

Discrete Controller Synthesis (DCS) is a powerful formal method for automatically generating specifications of discrete event systems. However, its practical adoption is often hindered by the highly specialized nature of formal models…

Large language models have gained significant traction and popularity in recent times, extending their usage to code-generation tasks. While this field has garnered considerable attention, the exploration of testing and evaluating the…

Eventual consistency is a more natural model than strong consistency for a distributed system, since it is closer to the underlying physical reality. Therefore, we propose that it is important to find a programming model that is both…