相关论文: Splitting source code identifiers using Bidirectio…

Software supply chain attacks targeting the npm ecosystem have become increasingly sophisticated, leveraging obfuscation and complex logic to evade traditional detection mechanisms. Recently, large language models (LLMs) have attracted…

The rapid proliferation of Large Language Models (LLMs) in software development has made distinguishing AI-generated code from human-written code a critical challenge with implications for academic integrity, code quality assurance, and…

Comprehensive specifications are essential for various activities across the entire validation continuum for system-on-chip (SoC) designs. However, specifications are often ambiguous, incomplete, or even contain inconsistencies or errors.…

Recent years have witnessed significant progress in developing deep learning-based models for automated code completion. Although using source code in GitHub has been a common practice for training deep-learning-based models for code…

Long short-term memory (LSTM) is a robust recurrent neural network architecture for learning spatiotemporal sequential data. However, it requires significant computational power for learning and implementing from both software and hardware…

We describe an LSTM-based model which we call Byte-to-Span (BTS) that reads text as bytes and outputs span annotations of the form [start, length, label] where start positions, lengths, and labels are separate entries in our vocabulary.…

Peer-to-peer distributed storage systems provide reliable access to data through redundancy spread over nodes across the Internet. A key goal is to minimize the amount of bandwidth used to maintain that redundancy. Storing a file using an…

This paper introduces a novel code-to-code search technique that enhances the performance of Large Language Models (LLMs) by including both static and dynamic features as well as utilizing both similar and dissimilar examples during…

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…

Large Language Models (LLMs) offer new potential for automating documentation-to-code traceability, yet their capabilities remain underexplored. We present a comprehensive evaluation of LLMs (Claude 3.5 Sonnet, GPT-4o, and o3-mini) in…

Extracting sections from clinical notes is crucial for downstream analysis but is challenging due to variability in formatting and labor-intensive nature of manual sectioning. While proprietary large language models (LLMs) have shown…

Large language models (LLMs) have shown impressive promise in code generation, yet their progress remains limited by the shortage of large-scale datasets that are both diverse and well-aligned with human reasoning. Most existing resources…

Learning representation for source code is a foundation of many program analysis tasks. In recent years, neural networks have already shown success in this area, but most existing models did not make full use of the unique structural…

We present a simple sequential sentence encoder for multi-domain natural language inference. Our encoder is based on stacked bidirectional LSTM-RNNs with shortcut connections and fine-tuning of word embeddings. The overall supervised model…

To drive progress in science and engineering, large language models (LLMs) must be able to process large amounts of numerical data and solve long calculations efficiently. This is currently only possible through the use of external tools or…

GitHub is the most widely used social, distributed version control system. It has around 10 million registered users and hosts over 16 million public repositories. Its user base is also very active as GitHub ranks in the top 100 Alexa most…

Design patterns provide reusable solutions to recurring software design problems. Automatically detecting these patterns in source code can help bootstrap new developers' understanding of unfamiliar software system architectures, and can…

Efficiency and safety of Large Language Models (LLMs), among other factors, rely on the quality of tokenization. A good tokenizer not only improves inference speed and language understanding but also provides extra defense against jailbreak…

Large Language Models (LLMs) for code are a family of high-parameter, transformer-based neural networks pre-trained on massive datasets of both natural and programming languages. These models are rapidly being employed in commercial…

Large Language Models (LLMs) have demonstrated strong capabilities in various natural language processing tasks; however, their application to graph-related problems remains limited, primarily due to scalability constraints and the absence…