相关论文: Can Highlighting Help GitHub Maintainers Track Sec…

Recent studies show LLMs struggle with complex instructions involving multiple constraints (e.g., length, format, sentiment). Existing works address this issue by fine-tuning, which heavily relies on fine-tuning data quality and is…

There is increasing evidence of Human Label Variation (HLV) in Natural Language Inference (NLI), where annotators assign different labels to the same premise-hypothesis pair. However, within-label variation--cases where annotators agree on…

Large Language Models (LLMs) have significantly advanced code completion, yet they often fail when the developer's intent is underspecified in the code context. To address this, developers usually add natural language instructions (e.g.,…

Deepfake has taken the world by storm, triggering a trust crisis. Current deepfake detection methods are typically inadequate in generalizability, with a tendency to overfit to image contents such as the background, which are frequently…

In software development, the predominant emphasis on functionality often supersedes security concerns, a trend gaining momentum with AI-driven automation tools like GitHub Copilot. These tools significantly improve developers' efficiency in…

Text watermarks for large language models (LLMs) have been commonly used to identify the origins of machine-generated content, which is promising for assessing liability when combating deepfake or harmful content. While existing…

Managing large numbers of incoming bug reports and finding the most critical issues in hardware development is time consuming, but crucial in order to reduce development costs. In this paper, we present an approach to predict the time to…

Forking is a common practice for developers when building upon on already existing projects. These forks create variants, which have a common code base but then evolve the code in different directions, which is specific to that forked…

The growing adoption of IT-systems for modeling and executing (business) processes or services has thrust the scientific investigation towards techniques and tools which support more complex forms of process analysis. Many of them, such as…

Large Language Model (LLM) reasoning for complex tasks inherently involves a trade-off between solution accuracy and computational efficiency. The subsequent step of verification, while intended to improve performance, further complicates…

Large Language Models (LLMs) fine-tuned to align with human values often exhibit alignment drift, producing unsafe or policy-violating completions when exposed to adversarial prompts, decoding perturbations, or paraphrased jailbreaks. While…

As the number of web applications and API endpoints exposed to the Internet continues to grow, so does the number of exploitable vulnerabilities. Manually identifying such vulnerabilities is tedious. Meanwhile, static security scanners tend…

Assuring traceability from requirements to implementation is a key element when developing safety critical software systems. Traditionally, this traceability is ensured by a waterfall-like process, where phases follow each other, and…

Despite significant advancements in the general capability of large language models (LLMs), they continue to struggle with consistent and accurate reasoning, especially in complex tasks such as mathematical and code reasoning. One key…

Although LLMs have shown promising potential in vulnerability detection, this study reveals their limitations in distinguishing between vulnerable and similar-but-benign patched code (only 0.06 - 0.14 accuracy). It shows that LLMs struggle…

[Background] In large open-source software projects, development knowledge is often fragmented across multiple artefacts and contributors such that individual stakeholders are generally unaware of the full breadth of the product features.…

With the recent advances in AI programming assistants such as GitHub Copilot, programming is not limited to classical programming languages anymore--programming tasks can also be expressed and solved by end-users in natural text. Despite…

Large Language Models (LLMs) have shown impressive proficiency in code generation. Unfortunately, these models share a weakness with their human counterparts: producing code that inadvertently has security vulnerabilities. These…

Multimodal retrieval models fail on reasoning-intensive queries where images (diagrams, charts, screenshots) must be deeply integrated with text to identify relevant documents -- the best multimodal model achieves only 27.6 nDCG@10 on…

As modern hardware designs grow in complexity and size, ensuring security across the confidentiality, integrity, and availability (CIA) triad becomes increasingly challenging. Information flow tracking (IFT) is a widely-used approach to…