Related papers: Knowledge Lever Risk Management for Software Engin…

Recent studies observe that reinforcement learning with verifiable rewards (RLVR) reliably improves pass@1 on reasoning tasks, yet often fails to yield comparable gains in pass@k, raising the question of whether RLVR genuinely enables large…

Autoregressive large language models (LLMs) pre-trained by next token prediction are inherently proficient in generative tasks. However, their performance on knowledge-driven tasks such as factual knowledge querying remains unsatisfactory.…

The preservation of intangible cultural heritage is a critical challenge as collective memory fades over time. While Large Language Models (LLMs) offer a promising avenue for generating engaging narratives, their propensity for factual…

Multimodal Large Language Models (MLLMs) are commonly derived by extending pre-trained Large Language Models (LLMs) with visual capabilities. In this work, we investigate how MLLMs process visual inputs by analyzing their attention…

Large Vision-Language Models (LVLMs) are widely adopted for their strong multimodal capabilities, yet they raise serious concerns such as privacy leakage and harmful content generation. Machine unlearning has emerged as a promising solution…

As the shortage of skilled workers continues to be a pressing issue, exacerbated by demographic change, it is becoming a critical challenge for organizations to preserve the knowledge of retiring experts and to pass it on to novices. While…

Context: Empirical Software Engineering (ESE) faces increasing challenges due to data scale, methodological complexity, and reproducibility concerns. Large Language Models (LLMs) have emerged as promising tools to support empirical…

Practical machine learning systems often operate in multiple sequential stages, as seen in ranking and recommendation systems, which typically include a retrieval phase followed by a ranking phase. Effectively assessing prediction…

Knowledge is fundamental to the overall capabilities of Large Language Models (LLMs). The knowledge paradigm of a model, which dictates how it encodes and utilizes knowledge, significantly affects its performance. Despite the continuous…

In an increasingly interconnected and data-driven world, the importance of robust security measures cannot be overstated. A knowledge graph constructed with information extracted from the system along with the desired security behavior can…

Managing data storage growth is of crucial importance to businesses. Poor practices can lead to large data and financial losses. Access to storage information along with timely action, or capacity forecasting, are essential to avoid these…

Machine unlearning has emerged as a prevalent technical solution for selectively removing unwanted knowledge absorbed during pre-training, without requiring full retraining. While recent unlearning techniques can effectively remove…

Secure software engineering is crucial but can be time-consuming; therefore, methods that could expedite the identification of software weaknesses without reducing the process efficacy would benefit the software engineering industry and…

Quantum computing, particularly in the area of quantum optimization, is steadily progressing toward practical applications, supported by an expanding range of hardware platforms and simulators. While Software Engineering (SE) optimization…

The Key-Value (KV) cache is integral to efficient autoregressive inference in large language models (LLMs), yet its unbounded growth in stateful multi-turn scenarios presents major challenges. This paper examines the interplay between KV…

Pre-trained language models (PLMs) have demonstrated strong performance in sequential recommendation (SR), which are utilized to extract general knowledge. However, existing methods still lack domain knowledge and struggle to capture users'…

Evaluating mathematical reasoning in LLMs is constrained by limited benchmark sizes and inherent model stochasticity, yielding high-variance accuracy estimates and unstable rankings across platforms. On difficult problems, an LLM may fail…

Although many efforts have been made, it is still a challenge to balance the training budget, downstream performance, and the general capabilities of the LLMs in many applications. Training the whole model for downstream tasks is expensive,…

As large language models (LLMs) are increasingly adopted in safety-critical and regulated sectors, the retention of sensitive or prohibited knowledge introduces escalating risks, ranging from privacy leakage to regulatory non-compliance to…

Event-related potentials (ERPs) extracted from electroencephalography (EEG) data in response to stimuli are widely used in psychological and neuroscience experiments. A major goal is to link ERP characteristic components to subject-level…