Related papers: Learning Project-wise Subsequent Code Edits via In…

The evolution of web applications relies on iterative code modifications, a process that is traditionally manual and time-consuming. While Large Language Models (LLMs) can generate UI code, their ability to edit existing code from new…

Instruction-based image editing models offer increased personalization opportunities in generative tasks. However, properly evaluating their results is challenging, and most of the existing metrics lag in terms of alignment with human…

In dynamic Industrial Internet of Things (IIoT) environments, models need the ability to selectively forget outdated or erroneous knowledge. However, existing methods typically rely on retain data to constrain model behavior, which…

Engineering information systems for scientific data analysis presents significant challenges: complex workflows requiring exploration of large solution spaces, close collaboration with domain specialists, and the need for maintainable,…

By augmenting Large Language Models (LLMs) with external tools, their capacity to solve complex problems has been significantly enhanced. However, despite ongoing advancements in the parsing capabilities of LLMs, incorporating all available…

Code snippet adaptation is a fundamental activity in the software development process. Unlike code generation, code snippet adaptation is not a "free creation", which requires developers to tailor a given code snippet in order to fit…

A significant amount of research is focused on developing and evaluating large language models for a variety of code synthesis tasks. These include synthesizing code from natural language, synthesizing tests from code, and synthesizing…

We introduce transductive program synthesis, a new formulation of the program synthesis task that explicitly leverages test inputs during synthesis. While prior approaches to program synthesis--whether based on natural language descriptions…

To reduce the latency associated with autoretrogressive LLM inference, speculative decoding has emerged as a novel decoding paradigm, where future tokens are drafted and verified in parallel. However, the practical deployment of speculative…

Tool learning has emerged as a promising paradigm for large language models (LLMs) to solve many real-world tasks. Nonetheless, with the tool repository rapidly expanding, it is impractical to contain all tools within the limited input…

In this paper, we present a novel approach to improving software quality and efficiency through a Large Language Model (LLM)-based model designed to review code and identify potential issues. Our proposed LLM-based AI agent model is trained…

This dissertation addresses achieving causal interpretability in Deep Learning for Software Engineering (DL4SE). While Neural Code Models (NCMs) show strong performance in automating software tasks, their lack of transparency in causal…

Evaluating open-ended outputs from large language models (LLMs) remains challenging due to the absence of ground truth. Existing metrics rely on final-answer accuracy or surface-level statistics, leaving the reasoning process itself…

Large language models (LLMs) has experienced exponential growth, they demonstrate remarkable performance across various tasks. Notwithstanding, contemporary research primarily centers on enhancing the size and quality of pretraining data,…

Estimating instruction-level throughput is critical for many applications: multimedia, low-latency networking, medical, automotive, avionic, and industrial control systems all rely on tightly calculable and accurate timing bounds of their…

Modern computing students often rely on both natural-language prompting and manual code editing to solve programming tasks. Yet we still lack a clear understanding of how these two modes are combined in practice, and how their usage varies…

Code editing constitutes a fundamental practice in software development, wherein developers modify existing codebases according to natural language requirements. Accurate code editing necessitates a comprehensive understanding of both the…

Humans write code in a fundamentally interactive manner and rely on constant execution feedback to correct errors, resolve ambiguities, and decompose tasks. While LLMs have recently exhibited promising coding capabilities, current coding…

Model editing aims to correct outdated or erroneous knowledge in large language models (LLMs) without the need for costly retraining. Lifelong model editing is the most challenging task that caters to the continuous editing requirements of…

The rise of large language models (LLMs) has led to dramatic improvements across a wide range of natural language tasks. Their performance on certain tasks can be further enhanced by incorporating test-time reasoning techniques. These…