Related papers: Adaptive Hierarchical Evaluation of LLMs and SAST …

Code analysis is fundamental in Software Engineering, supporting debugging, optimization, and security assessment. Human developers approach it through syntax parsing, static semantics inference, and dynamic reasoning. Traditional tools are…

Log Anomaly Detection (LAD) seeks to identify atypical patterns in log data that are crucial to assessing the security and condition of systems. Although Large Language Models (LLMs) have shown tremendous success in various fields, the use…

The alignment of large language models (LLMs) is crucial not only for unlocking their potential in specific tasks but also for ensuring that responses meet human expectations and adhere to safety and ethical principles. Current alignment…

Pre-trained gaze models learn to identify useful patterns commonly found across users, but subtle user-specific variations (i.e., eyelid shape or facial structure) can degrade model performance. Test-time personalization (TTP) adapts…

Although Large Language Models (LLMs) excel in NLP tasks, they still need external tools to extend their ability. Current research on tool learning with LLMs often assumes mandatory tool use, which does not always align with real-world…

Pre-training Large Language Models (LLMs) on web-scale datasets becomes fundamental for advancing general-purpose AI. In contrast, enhancing their predictive performance on downstream tasks typically involves adapting their knowledge…

Large Language Models (LLMs) have shown significant potential as judges for Machine Translation (MT) quality assessment, providing both scores and fine-grained feedback. Although approaches such as GEMBA-MQM have shown state-of-the-art…

Large Language Model (LLM) inference systems present significant challenges in statistical performance characterization due to dynamic workload variations, diverse hardware architectures, and complex interactions between model size, batch…

The current cybersecurity landscape is increasingly complex, with traditional Static Application Security Testing (SAST) tools struggling to capture complex and emerging vulnerabilities due to their reliance on rule-based matching.…

Low-rank adaptation (LoRA) has emerged as the de facto standard for parameter-efficient fine-tuning (PEFT) of foundation models, enabling the adaptation of billion-parameter networks with minimal computational and memory overhead. Despite…

Large Language Models (LLMs) have demonstrated remarkable performance across a broad spectrum of tasks, including natural language understanding, dialogue systems, and code generation. Despite evident progress, less attention has been paid…

Discovering effective predictive signals, or "alphas," from financial data with high dimensionality and extremely low signal-to-noise ratio remains a difficult open problem. Despite progress in deep learning, genetic programming, and, more…

Artifact Evaluation (AE) is essential for ensuring the transparency and reliability of research, closing the gap between exploratory work and real-world deployment is particularly important in cybersecurity, particularly in IoT and CPSs,…

The prevalence of security vulnerabilities has prompted companies to adopt static application security testing (SAST) tools for vulnerability detection. Nevertheless, these tools frequently exhibit usability limitations, as their generic…

Recent advances in mechanistic interpretability have highlighted the potential of automating interpretability pipelines in analyzing the latent representations within LLMs. While this may enhance our understanding of internal mechanisms,…

Large language models (LLMs) have recently shown great advances in a variety of tasks, including natural language understanding and generation. However, their use in high-stakes decision-making scenarios is still limited due to the…

While code review is central to the software development process, it can be tedious and expensive to carry out. In this paper, we investigate whether and how Large Language Models (LLMs) can aid with code reviews. Our investigation focuses…

Large Language Models (LLMs) have demonstrated significant potential in automated software security, particularly in vulnerability detection. However, existing benchmarks primarily focus on isolated, single-vulnerability samples or…

Alignment faking (AF) occurs when an LLM strategically complies with training objectives to avoid value modification, reverting to prior preferences once monitoring is lifted. Current detection methods focus on conversational settings and…

The rapid advancement of Large Language Models (LLMs) in software engineering has revealed critical limitations in existing benchmarks, particularly the widely used SWE-bench dataset. Recent studies have uncovered severe data contamination…