Related papers: When simplicity meets effectiveness: Detecting cod…
Source code clones pose risks ranging from intellectual property violations to unintended vulnerabilities. Effective and efficient scalable clone detection, especially for diverged clones, remains challenging. Large language models (LLMs)…
Semantic code search has been widely adopted in both academia and industry. These approaches embed natural-language queries and code snippets into a shared embedding space and retrieve results based on vector similarity. Despit strong…
Watermarking large language models (LLMs) is vital for preventing their misuse, including the fabrication of fake news, plagiarism, and spam. It is especially important to watermark LLM-generated code, as it often contains intellectual…
Detecting structural similarity between queries is essential for selecting examples in in-context learning models. However, assessing structural similarity based solely on the natural language expressions of queries, without considering SQL…
In modern software development, developers frequently need to understand code behavior at a glance -- whether reviewing pull requests, debugging issues, or navigating unfamiliar codebases. This ability to reason about dynamic program…
Code refinement aims to enhance existing code by addressing issues, refactoring, and optimizing to improve quality and meet specific requirements. As software projects scale in size and complexity, the traditional iterative exchange between…
Sentiment analysis (SA) using code-mixed data from social media has several applications in opinion mining ranging from customer satisfaction to social campaign analysis in multilingual societies. Advances in this area are impeded by the…
Detecting semantic similarities between sentences is still a challenge today due to the ambiguity of natural languages. In this work, we propose a simple approach to identifying semantically similar questions by combining the strengths of…
Large Language Models (LLMs) have shown remarkable capabilities in processing both natural and programming languages, which have enabled various applications in software engineering, such as requirement engineering, code generation, and…
Inductive program synthesis, or programming by example, requires synthesizing functions from input-output examples that generalize to unseen inputs. While large language model agents have shown promise in programming tasks guided by natural…
Text-to-3D generation from a single-view image is a popular but challenging task in 3D vision. Although numerous methods have been proposed, existing works still suffer from the inconsistency issues, including 1) semantic inconsistency, 2)…
Trustworthy evaluation methods for code snippets play a crucial role in neural code generation. Traditional methods, which either rely on reference solutions or require executable test cases, have inherent limitation in flexibility and…
Consensus is an often occurring problem in concurrent and distributed programming. We present a programming language with simple semantics and build-in support for consensus in the form of communicating transactions. We motivate the need…
Software security vulnerabilities can lead to severe consequences, making early detection essential. Although code review serves as a critical defense mechanism against security flaws, relevant feedback remains scarce due to limited…
Developers often write low-quality code comments due to the lack of programming experience, which can reduce the efficiency of developers program comprehension. Therefore, developers hope that code comment generation tools can be developed…
Neural program embedding can be helpful in analyzing large software, a task that is challenging for traditional logic-based program analyses due to their limited scalability. A key focus of recent machine-learning advances in this area is…
With the involvement of multiple programming languages in modern software development, cross-lingual code clone detection has gained traction within the software engineering community. Numerous studies have explored this topic, proposing…
Recent advances in large language models (LLMs) have shown that test-time scaling can substantially improve model performance on complex tasks, particularly in the coding domain. Under this paradigm, models use a larger token budget during…
While large code language models have made significant strides in AI-assisted coding tasks, there are growing concerns about privacy challenges. The user code is transparent to the cloud LLM service provider, inducing risks of unauthorized…
Motivation: Code understandability is crucial in software development, as developers spend 58% to 70% of their time reading source code. Improving it can improve productivity and reduce maintenance costs. Problem: Experimental studies often…