相关论文: Towards Bridging Formal Methods and Human Interpre…

Cross-Lingual Text Simplification (CLTS) aims to make content more accessible across languages by simultaneously addressing both linguistic complexity and translation. This study investigates the effectiveness of different prompting…

Software developers and maintainers need to read and understand source programs and other software artifacts. The increase in size and complexity of software drastically affects several quality attributes, especially understandability and…

Serendipity plays a pivotal role in enhancing user satisfaction within recommender systems, yet its evaluation poses significant challenges due to its inherently subjective nature and conceptual ambiguity. Current algorithmic approaches…

Boundary value analysis and testing (BVT) is fundamental in software quality assurance because faults tend to cluster at input extremes, yet testers often struggle to understand and justify why certain input-output pairs represent…

We propose \textbf{Cognitive Load Traces} (CLTs) as a mid-level interpretability framework for deep models, inspired by Cognitive Load Theory in human cognition. CLTs are defined as symbolic, temporally varying functions that quantify…

This study presents a framework for automated evaluation of dynamically evolving topic taxonomies in scientific literature using Large Language Models (LLMs). In digital library systems, topic modeling plays a crucial role in efficiently…

Transfer learning (TL) has been widely used in motor imagery (MI) based brain-computer interfaces (BCIs) to reduce the calibration effort for a new subject, and demonstrated promising performance. While a closed-loop MI-based BCI system,…

Classical computation, grounded in formal, logical systems, has been the engine of technological progress for decades, excelling at problems that can be described with unambiguous rules. This paradigm, however, leaves a vast ocean of human…

Annotated data has become the most important bottleneck in training accurate machine learning models, especially for areas that require domain expertise. A recent approach to deal with the above issue proposes using natural language…

Large Language Models (LLMs) are not only resource-intensive to train but even more costly to deploy in production. Therefore, recent work has attempted to prune blocks of LLMs based on cheap proxies for estimating block importance,…

Test-time scaling (TTS) has recently emerged as a promising direction to exploit the hidden reasoning capabilities of pre-trained large language models (LLMs). However, existing scaling methods narrowly focus on the compute-optimal…

Large language models (LLMs) are increasingly used in software development, but their level of software security expertise remains unclear. This work systematically evaluates the security comprehension of five leading LLMs: GPT-4o-Mini,…

While many researchers use Large Language Models (LLMs) through chat-based access, their real potential lies in leveraging LLMs via application programming interfaces (APIs). This paper conceptualizes LLMs as universal text processing…

Context: Linear Temporal Logic (LTL) has been used widely in verification. Its importance and popularity have only grown with the revival of temporal logic synthesis, and with new uses of LTL in robotics and planning activities. All these…

We investigate how well large language models (LLMs) generalize across different task difficulties, a key question for effective data curation and evaluation. Existing research is mixed regarding whether training on easier or harder data…

We study the problem of stabilizing an unknown partially observable linear time-invariant (LTI) system. For fully observable systems, leveraging an unstable/stable subspace decomposition approach, state-of-art sample complexity is…

Propositional Linear Temporal Logic (LTL) is a popular formalism for specifying desirable requirements and security and privacy policies for software, networks, and systems. Yet expressing such requirements and policies in LTL remains…

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…

Stereotypes are generalised assumptions about societal groups, and even state-of-the-art LLMs using in-context learning struggle to identify them accurately. Due to the subjective nature of stereotypes, where what constitutes a stereotype…

Large language models (LLMs) are capable of solving a wide range of tasks, yet they have struggled with reasoning. To address this, we propose $\textbf{Additional Logic Training (ALT)}$, which aims to enhance LLMs' reasoning capabilities by…