相关论文: Context-Specific Instruction: A Longitudinal Study…

Debugging is an essential skill when learning to program, yet its instruction and emphasis often vary widely across introductory courses. In the era of code-generating large language models (LLMs), the ability for students to reason about…

Code language models have emerged as useful tools for various programming tasks, yet they often struggle when it comes to complex ones. In this paper, we explore the potential of curriculum learning in enhancing the performance of these…

Current AI-powered code assistance tools often struggle with poorly-defined problem statements that lack sufficient task context and requirements specification. Recent analysis of software engineering agents reveals that failures on such…

Identifying and resolving logic errors can be one of the most frustrating challenges for novices programmers. Unlike syntax errors, for which a compiler or interpreter can issue a message, logic errors can be subtle. In certain conditions,…

Bug localization aims to reduce debugging time by recommending program elements that are relevant for a specific bug report. To date, researchers have primarily addressed this problem by applying different information retrieval techniques…

Language models (LMs) have shown impressive performance on tasks within their training distribution, but often struggle with structurally novel tasks even when given a small number of in-context task examples. We investigate the…

Recent approaches to real-time long video generation typically employ streaming tuning strategies, attempting to train a long-context student using a short-context (memoryless) teacher. In these frameworks, the student performs long…

Context: Issue tracking systems are used to track and describe tasks in the development process, e.g., requested feature improvements or reported bugs. However, past research has shown that the reported issue types often do not match the…

Automated program repair is a crucial task for improving the efficiency of software developers. Recently, neural-based techniques have demonstrated significant promise in generating correct patches for buggy code snippets. However, most…

Language models significantly benefit from context tokens, such as prompts or scratchpads. They perform better when prompted with informative instructions, and they acquire new reasoning capabilities by generating a scratch-pad before…

Context: Software performance is a critical non-functional requirement, appearing in many fields such as mission critical applications, financial, and real time systems. In this work we focused on early detection of performance bugs; our…

Natural language elements in source code, e.g., the names of variables and functions, convey useful information. However, most existing bug detection tools ignore this information and therefore miss some classes of bugs. The few existing…

Traditional security scanners fail when facing new attack patterns they haven't seen before. They rely on fixed rules and predetermined signatures, making them blind to novel threats. We present a fundamentally different approach: instead…

Large Language Models (LLMs) have demonstrated remarkable performance in code completion. However, the training data used to develop these models often contain a significant amount of buggy code. Yet, it remains unclear to what extent these…

Debugging is a central yet complex activity in software engineering. Prior studies have documented debugging strategies and tool usage, but little theory explains how experienced developers reason about bugs in large, real-world codebases.…

Automated test generators, such as search based software testing (SBST) techniques, replace the tedious and expensive task of manually writing test cases. SBST techniques are effective at generating tests with high code coverage. However,…

Context: Specification mining techniques are typically used to extract the specification of a software in the absence of (up-to-date) specification documents. This is useful for program comprehension, testing, and anomaly detection.…

Semantic segmentation is still a challenging task for parsing diverse contexts in different scenes, thus the fixed classifier might not be able to well address varying feature distributions during testing. Different from the mainstream…

Recently, pretrained language models have shown state-of-the-art performance on the vulnerability detection task. These models are pretrained on a large corpus of source code, then fine-tuned on a smaller supervised vulnerability dataset.…

Pre-trained Large Language Models (LLMs) require post-training methods such as supervised fine-tuning (SFT) on instruction-response pairs to enable instruction following. However, this process can potentially harm existing capabilities…