Related papers: MENTOR: A Metacognition-Driven Self-Evolution Fram…

Recent explorations with commercial Large Language Models (LLMs) have shown that non-expert users can jailbreak LLMs by simply manipulating their prompts; resulting in degenerate output behavior, privacy and security breaches, offensive…

Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produce harmful, restricted, or biased content. In this paper, we…

Efficient red-teaming method to uncover vulnerabilities in Large Language Models (LLMs) is crucial. While recent attacks often use LLMs as optimizers, the discrete language space make gradient-based methods struggle. We introduce LARGO…

Large Language Models (LLMs) fine-tuned for specific domains exhibit strong performance; however, the underlying mechanisms by which this fine-tuning reshapes their parametric space are not well understood. Prior works primarily focus on…

The widespread applications of large language models (LLMs) have brought about concerns regarding their potential misuse. Although aligned with human preference data before release, LLMs remain vulnerable to various malicious attacks. In…

Large Language Models (LLMs) rapidly reshape modern life, advancing fields from healthcare to education and beyond. However, alongside their remarkable capabilities lies a significant threat: the susceptibility of these models to…

Jailbreaking in Large Language Models (LLMs) is a major security concern as it can deceive LLMs to generate harmful text. Yet, there is still insufficient understanding of how jailbreaking works, which makes it hard to develop effective…

In this paper we propose a formal, model-agnostic meta-learning framework for safe reinforcement learning. Our framework is inspired by how parents safeguard their children across a progression of increasingly riskier tasks, imparting a…

Large language models (LLMs) often generate inaccurate or fabricated information and generally fail to indicate their confidence, which limits their broader applications. Previous work elicits confidence from LLMs by direct or…

Large Language Models (LLMs) have demonstrated promising capabilities in solving mathematical reasoning tasks, leveraging Chain-of-Thought (CoT) data as a vital component in guiding answer generation. Current paradigms typically generate…

Integrated Speech and Large Language Models (SLMs) that can follow speech instructions and generate relevant text responses have gained popularity lately. However, the safety and robustness of these models remains largely unclear. In this…

With the widespread deployment of Multimodal Large Language Models (MLLMs) for visual-reasoning tasks, improving their safety has become crucial. Recent research indicates that despite training-time safety alignment, these models remain…

Multimodal large language models (MLLMs) have shown remarkable capabilities in multimodal perception and understanding tasks. However, their effectiveness in specialized domains, such as remote sensing and medical imaging, remains limited.…

Reinforcement learning (RL) agents with pre-specified reward functions cannot provide guaranteed safety across variety of circumstances that an uncertain system might encounter. To guarantee performance while assuring satisfaction of safety…

Large Language Models (LLMs) are vulnerable to adversarial attacks that bypass safety guidelines and generate harmful content. Mitigating these vulnerabilities requires defense mechanisms that are both robust and computationally efficient.…

Large Language Models (LLMs) have exhibited great performance in autonomously calling various tools in external environments, leading to better problem solving and task automation capabilities. However, these external tools also amplify…

Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks. Nevertheless, they still pose notable safety risks due to potential misuse for malicious purposes. Jailbreaking, which seeks to induce models to…

Large language models (LLMs) have revolutionized algorithm development, yet their application in symbolic regression, where algorithms automatically discover symbolic expressions from data, remains limited. In this paper, we propose a…

Steering, or direct manipulation of internal activations to guide LLM responses toward specific semantic concepts, is emerging as a promising avenue for both understanding how semantic concepts are stored within LLMs and advancing LLM…

Large Language Models (LLMs) excel at general code generation, but their performance drops sharply in enterprise settings that rely on internal private libraries absent from public pre-training corpora. While Retrieval-Augmented Generation…