Related papers: Logical Segmentation of Source Code

Developers spend much of their time reading and browsing source code, raising new opportunities for summarization methods. Indeed, modern code editors provide code folding, which allows one to selectively hide blocks of code. However this…

Code generation, the task of creating executable programs from natural language requirements, has recently seen tremendous advances through Chain-of-Thought (CoT) reasoning, which enables Large Language Models (LLMs) to develop high-level…

In source code search, a common information-seeking strategy involves providing a short initial query with a broad meaning, and then iteratively refining the query using terms gleaned from the results of subsequent searches. This strategy…

In this paper we present an alternative method to symbolic segmentation: we approach symbolic segmentation as an algorithm selection problem. That is, let there be a set A of available algorithms for symbolic segmentation, a set of input…

Distribution shift has been a longstanding challenge for the reliable deployment of deep learning (DL) models due to unexpected accuracy degradation. Although DL has been becoming a driving force for large-scale source code analysis in the…

Traditional formal specification generation methods are typically tailored to specific specification types, and therefore suffer from limited generality. In recent years, large language model (LLM)-based specification generation approaches…

Code data has been shown to enhance the reasoning capabilities of large language models (LLMs), but it remains unclear which aspects of code are most responsible. We investigate this question with a systematic, data-centric framework. We…

Code Large Language Models (Code LLMs) have opened a new era in programming with their impressive capabilities. However, recent research has revealed critical limitations in their ability to reason about runtime behavior and understand the…

In many sequence learning tasks, such as program synthesis and document summarization, a key problem is searching over a large space of possible output sequences. We propose to learn representations of the outputs that are specifically…

The machine learning community has been overwhelmed by a plethora of deep learning based approaches. Many challenging computer vision tasks such as detection, localization, recognition and segmentation of objects in unconstrained…

Large Language Models (LLMs) have shown remarkable capabilities in code generation tasks, yet they face significant limitations in handling complex, long-context programming challenges and demonstrating complex compositional reasoning…

Code generation is to automatically generate source code conforming to a given programming specification, which has received extensive attention especially with the development of large language models (LLMs). Due to the inherent difficulty…

Code provides a general syntactic structure to build complex programs and perform precise computations when paired with a code interpreter - we hypothesize that language models (LMs) can leverage code-writing to improve Chain of Thought…

Distributed computation is a framework used to break down a complex computational task into smaller tasks and distributing them among computational nodes. Erasure correction codes have recently been introduced and have become a popular…

Code review is a crucial practice in software development. As code review nowadays is lightweight, various issues can be identified, and sometimes, they can be trivial. Research has investigated automated approaches to classify review…

Large language models (LLMs) have shown promising results for software engineering applications, but still struggle with code reasoning tasks such as vulnerability detection (VD). We introduce ConceptCoder, a fine-tuning method that…

Algorithmic reasoning refers to the ability to understand the complex patterns behind the problem and decompose them into a sequence of reasoning steps towards the solution. Such nature of algorithmic reasoning makes it a challenge for…

We study segmented burst-deletion channels motivated by the observation that synchronization errors commonly occur in a bursty manner in real-world settings. In this channel model, transmitted sequences are implicitly divided into…

(Source) code search is widely concerned by software engineering researchers because it can improve the productivity and quality of software development. Given a functionality requirement usually described in a natural language sentence, a…

Source code summarization is the task of generating a high-level natural language description for a segment of programming language code. Current neural models for the task differ in their architecture and the aspects of code they consider.…