Related papers: Synthesis of Mathematical programs from Natural La…

We present a framework for training trustworthy large language model (LLM) agents for optimization modeling via a verifiable synthetic data generation pipeline. Focusing on linear and mixed-integer linear programming, our approach begins…

With the decline of Moore's law, optimizing program performance has become a major focus of software research. However, high-level optimizations such as API and algorithm changes remain elusive due to the difficulty of understanding the…

Current approaches to program synthesis with Large Language Models (LLMs) exhibit a "near miss syndrome": they tend to generate programs that semantically resemble the correct answer (as measured by text similarity metrics or human…

Probabilistic programs are key to deal with uncertainty in e.g. controller synthesis. They are typically small but intricate. Their development is complex and error prone requiring quantitative reasoning over a myriad of alternative…

Program Synthesis is the task of generating a program from a provided specification. Traditionally, this has been treated as a search problem by the programming languages (PL) community and more recently as a supervised learning problem by…

To support software developers in understanding and maintaining programs, various automatic (source) code summarization techniques have been proposed to generate a concise natural language summary (i.e., comment) for a given code snippet.…

Automating code documentation through explanatory text can prove highly beneficial in code understanding. Large Language Models (LLMs) have made remarkable strides in Natural Language Processing, especially within software engineering tasks…

Despite great advances in program synthesis techniques, they remain algorithmic black boxes. Although they guarantee that when synthesis is successful, the implementation satisfies the specification, they provide no additional information…

We introduce KodCode, a synthetic dataset that addresses the persistent challenge of acquiring high-quality, verifiable training data across diverse difficulties and domains for training Large Language Models for coding. Existing…

In program synthesis, we transform a specification into a program that is guaranteed to satisfy the specification. In synthesis of reactive systems, the environment in which the program operates may behave nondeterministically, e.g., by…

Effective code documentation is essential for collaboration, comprehension, and long-term software maintainability, yet developers often neglect it due to its repetitive nature. Automated documentation generation has evolved from heuristic…

Grammatical error correction, like other machine learning tasks, greatly benefits from large quantities of high quality training data, which is typically expensive to produce. While writing a program to automatically generate realistic…

While deep learning approaches to information extraction have had many successes, they can be difficult to augment or maintain as needs shift. Rule-based methods, on the other hand, can be more easily modified. However, crafting rules…

Computational models of human language often involve combinatorial problems. For instance, a probabilistic parser may marginalize over exponentially many trees to make predictions. Algorithms for such problems often employ dynamic…

Natural language (NL) to code suggestion systems assist developers in Integrated Development Environments (IDEs) by translating NL utterances into compilable code snippet. The current approaches mainly involve hard-coded, rule-based systems…

Code summarization is a critical task in natural language processing and software engineering, which aims to generate concise descriptions of source code. Recent advancements have improved the quality of these summaries, enhancing code…

In this research we use a data stream approach to mining data and construct Decision Tree models that predict software build outcomes in terms of software metrics that are derived from source code used in the software construction process.…

In earlier work, we developed an approach for automatic complexity analysis of integer programs, based on an alternating modular inference of upper runtime and size bounds for program parts. In this paper, we show how recent techniques to…

Large Language Models (LLMs) have demonstrated exceptional capabilities in various natural language tasks, often achieving performances that surpass those of humans. Despite these advancements, the domain of mathematics presents a…

Generative neural models hold great promise in enhancing programming education by synthesizing new content. We seek to design neural models that can automatically generate programming tasks for a given specification in the context of visual…