相关论文: Context-Aware Hierarchical Learning: A Two-Step Pa…
Recent studies reveal that integrating new modalities into Large Language Models (LLMs), such as Vision-Language Models (VLMs), creates a new attack surface that bypasses existing safety training techniques like Supervised Fine-tuning (SFT)…
The rapid evolution of Large Language Models (LLMs) into autonomous, tool-calling agents has fundamentally altered the cybersecurity landscape. Frameworks like OpenClaw grant AI systems operating-system-level permissions and the autonomy to…
Vision-Language-Action systems follow instructions to execute multi-step tasks in multimodal environments. Recent VLA approaches typically rely on post-hoc correction mechanisms or operate under fixed task decompositions and alignment…
This thesis investigates two key phenomena in large language models (LLMs): in-context learning (ICL) and model collapse. We study ICL in a linear transformer with tied weights trained on linear regression tasks, and show that minimising…
The safety and robustness of large language models (LLMs) based applications remain critical challenges in artificial intelligence. Among the key threats to these applications are prompt hacking attacks, which can significantly undermine…
Currently, open-sourced large language models (OSLLMs) have demonstrated remarkable generative performance. However, as their structure and weights are made public, they are exposed to jailbreak attacks even after alignment. Existing…
The ability of Large Language Models (LLMs) to process and generate coherent text is markedly weakened when the number of input tokens exceeds their pretraining length. Given the expensive overhead of finetuning large-scale models with…
Hierarchical Multi-Label Classification (HMC) faces critical challenges in maintaining structural consistency and balancing loss weighting in Multi-Task Learning (MTL). In order to address these issues, we propose a classifier called HCAL…
We investigate long-context vulnerabilities in Large Language Models (LLMs) through Many-Shot Jailbreaking (MSJ). Our experiments utilize context length of up to 128K tokens. Through comprehensive analysis with various many-shot attack…
Understanding in-context learning (ICL) capability that enables large language models (LLMs) to excel in proficiency through demonstration examples is of utmost importance. This importance stems not only from the better utilization of this…
In-context learning (ICL) enables large language models (LLMs) to perform downstream tasks through advanced prompting and high-quality demonstrations. However, traditional ICL paradigms encounter significant limitations in complex reasoning…
The tool-use ability of Large Language Models (LLMs) has a profound impact on a wide range of industrial applications. However, LLMs' self-control and calibration capability in appropriately using tools remains understudied. The problem is…
Long-context understanding has emerged as a critical capability for large language models (LLMs). However, evaluating this ability remains challenging. We present SCALAR, a benchmark designed to assess citation-grounded long-context…
Adapting Large Language Models (LLMs) to specific tasks introduces concerns about computational efficiency, prompting an exploration of efficient methods such as In-Context Learning (ICL). However, the vulnerability of ICL to privacy…
Pre-trained vision-language models (VLMs) have showcased remarkable performance in image and natural language understanding, such as image captioning and response generation. As the practical applications of vision-language models become…
Multimodal in-context learning (ICL) has emerged as a key mechanism for harnessing the capabilities of large vision-language models (LVLMs). However, its effectiveness remains highly sensitive to the quality of input ICL sequences,…
Although Large Language Models (LLMs) have demonstrated impressive text generation capabilities, they are easily misled by untruthful contexts provided by users or knowledge augmentation tools, leading to hallucinations. To alleviate LLMs…
Jailbreak attacks on large language models (LLMs) involve inducing these models to generate harmful content that violates ethics or laws, posing a significant threat to LLM security. Current jailbreak attacks face two main challenges: low…
Large Language models (LLMs) have achieved encouraging results in tabular data generation. However, existing approaches require fine-tuning, which is computationally expensive. This paper explores an alternative: prompting a fixed LLM with…
Large Language Models (LLMs) have the impressive ability to perform in-context learning (ICL) from only a few examples, but the success of ICL varies widely from task to task. Thus, it is important to quickly determine whether ICL is…