相关论文: AtP*: An efficient and scalable method for localiz…

Large Language Models (LLMs) are scaling rapidly, creating significant challenges for collaborative server client distributed training, particularly in terms of communication efficiency and computational overheads. To address these…

Penetration testing is essential to securing modern web infrastructures, yet traditional manual methods struggle to keep pace with their scale and complexity. Large Language Models (LLMs) offer new opportunities for automating these tasks,…

Prompt engineering and finetuning aim to maximize language model performance on a given metric (like toxicity reduction). However, these methods do not fully elicit a model's capabilities. To reduce this gap, we introduce activation…

Large language models (LLMs) often suffer from hallucinations due to error accumulation in autoregressive decoding, where suboptimal early token choices misguide subsequent generation. Although multi-path decoding can improve robustness by…

Detectability of failures of linear programming (LP) decoding and its potential for improvement by adding new constraints motivate the use of an adaptive approach in selecting the constraints for the LP problem. In this paper, we make a…

Large Language Models (LLMs) have demonstrated considerable advances, and several claims have been made about their exceeding human performance. However, in real-world tasks, domain knowledge is often required. Low-resource learning methods…

Aim: With the advent of LLMs, sophisticated agentic program repair has become viable at large organizations with large codebases. In this work, we develop an Engineering Agent that fixes the source code based on test failures at scale…

Jailbreak vulnerabilities in Large Language Models (LLMs) refer to methods that extract malicious content from the model by carefully crafting prompts or suffixes, which has garnered significant attention from the research community.…

Existing research on large language models (LLMs) for automated code compliance has primarily focused on performance, treating the models as black boxes and overlooking how training decisions affect their interpretive behavior. This paper…

Large Language Models (LLMs) have demonstrated remarkable performance in various natural language processing tasks. However, the training of these models is computationally intensive and susceptible to faults, particularly in the attention…

Activation sparsity is a promising approach for accelerating large language model (LLM) inference by reducing computation and memory movement. However, existing activation sparsity methods typically apply uniform sparsity across…

Aligning large language models (LLMs) depends on high-quality datasets of human preference labels, which are costly to collect. Although active learning has been studied to improve sample efficiency relative to passive collection, many…

Recent advances in Large Language Models (LLMs) have spurred transformative applications in various domains, ranging from open-source to proprietary LLMs. However, jailbreak attacks, which aim to break safety alignment and user compliance…

The activation function plays a crucial role in model optimisation, yet the optimal choice remains unclear. For example, the Sigmoid activation is the de-facto activation in balanced classification tasks, however, in imbalanced…

Large Language Models (LLMs) are widely deployed in real-world applications, yet their internal mechanisms remain difficult to interpret and control, limiting our ability to diagnose and correct undesirable behaviors. Mechanistic…

Effective social intelligence simulation requires language agents to dynamically adjust reasoning depth, a capability notably absent in current studies. Existing methods either lack explicit reasoning or employ lengthy Chain-of-Thought…

The increased use of Large Language Models (LLMs) in geography raises substantial questions about the safety of integrating these tools across a wide range of processes and analyses, given our very limited understanding of their inner…

Test-Time Scaling (TTS) improves the reasoning performance of Large Language Models (LLMs) by allocating additional compute during inference. We conduct a structured survey of TTS methods and categorize them into sampling-based,…

Aligning general-purpose large language models (LLMs) to downstream tasks often incurs significant training adjustment costs. Prior research has explored various avenues to enhance alignment efficiency, primarily through minimal-data…

Deep neural networks have recently achieved competitive accuracy for human activity recognition. However, there is room for improvement, especially in modeling long-term temporal importance and determining the activity relevance of…