相关论文: Software Vulnerability Prediction in Low-Resource …

Large Language Models (LLMs) are increasingly used in software security, but their trustworthiness in generating accurate vulnerability advisories remains uncertain. This study investigates the ability of ChatGPT to (1) generate plausible…

The latest breakthroughs in large language models (LLM) have empowered software development tools, such as ChatGPT, to aid developers in complex tasks. Developers use ChatGPT to write code, review code changes, and even debug their…

This paper presents a comprehensive empirical analysis of security vulnerabilities in AI-generated code across public GitHub repositories. We collected and analyzed 7,703 files explicitly attributed to four major AI tools: ChatGPT…

Artificial Intelligence has demonstrated its significance in software engineering through notable improvements in productivity, accuracy, collaboration, and learning outcomes. This study examines the impact of generative AI tools,…

We investigate the problem of determining the predictive confidence (or, conversely, uncertainty) of a neural classifier through the lens of low-resource languages. By training models on sub-sampled datasets in three different languages, we…

Large Language Models (LLMs) have demonstrated remarkable success in various natural language processing and software engineering tasks, such as code generation. The LLMs are mainly utilized in the prompt-based zero/few-shot paradigm to…

This paper simulates a low-resource setting across 17 languages in order to evaluate embedding similarity, stability, and reliability under different conditions. The goal is to use corpus similarity measures before training to predict…

Despite the widespread adoption of Large Language Models (LLMs), their strongest capabilities remain largely confined to a small number of high-resource languages for which there is abundant training data. Recently, continual pre-training…

The training data for LLMs embeds societal values, increasing their familiarity with the language's culture. Our analysis found that 44% of the variance in the ability of GPT-4o to reflect the societal values of a country, as measured by…

Context: Traditional software security analysis methods struggle to keep pace with the scale and complexity of modern codebases, requiring intelligent automation to detect, assess, and remediate vulnerabilities more efficiently and…

The large-scale deployment of Solidity smart contracts on the Ethereum mainnet has increasingly attracted financially-motivated attackers in recent years. A few now-infamous attacks in Ethereum's history includes DAO attack in 2016 (50…

Unlike mainstream languages (such as English and French), low-resource languages often suffer from a lack of expert-annotated corpora and benchmark resources that make it hard to apply state-of-the-art techniques directly. In this paper, we…

Software libraries play a critical role in the functionality, efficiency, and maintainability of software systems. As developers increasingly rely on Large Language Models (LLMs) to streamline their coding processes, the effectiveness of…

Over the past few years, Large Language Models of Code (Code LLMs) have started to have a significant impact on programming practice. Code LLMs are also emerging as building blocks for research in programming languages and software…

Adapting large language models (LLMs) to new languages typically involves continual pre-training (CT) followed by supervised fine-tuning (SFT). However, this CT-then-SFT approach struggles with limited data in the context of low-resource…

This paper presents a comprehensive evaluation of the code generation capabilities of ChatGPT, a prominent large language model, compared to human programmers. A novel dataset of 131 code-generation prompts across 5 categories was curated…

Inspired by a new coded computation algorithm for invertible functions, we propose Coded-InvNet a new approach to design resilient prediction serving systems that can gracefully handle stragglers or node failures. Coded-InvNet leverages…

The data scarcity in low-resource languages has become a bottleneck to building robust neural machine translation systems. Fine-tuning a multilingual pre-trained model (e.g., mBART (Liu et al., 2020)) on the translation task is a good…

Background: Static Application Security Testing (SAST) tools purport to assist developers in detecting security issues in source code. These tools typically use rule-based approaches to scan source code for security vulnerabilities.…

This report provides a preliminary evaluation of ChatGPT for machine translation, including translation prompt, multilingual translation, and translation robustness. We adopt the prompts advised by ChatGPT to trigger its translation ability…