Related papers: SafeMind: Benchmarking and Mitigating Safety Risks…

Prompt design significantly impacts the moral competence and safety alignment of large language models (LLMs), yet empirical comparisons remain fragmented across datasets and models.We introduce ProMoral-Bench, a unified benchmark…

In embodied artificial intelligence, enabling heterogeneous robot teams to execute long-horizon tasks from high-level instructions remains a critical challenge. While large language models (LLMs) show promise in instruction parsing and…

Large language models (LLMs) have achieved remarkable capabilities but remain vulnerable to adversarial prompts known as jailbreaks, which can bypass safety alignment and elicit harmful outputs. Despite growing efforts in LLM safety…

With the continuous development of large language models (LLMs), transformer-based models have made groundbreaking advances in numerous natural language processing (NLP) tasks, leading to the emergence of a series of agents that use LLMs as…

The evaluation and improvement of medical large language models (LLMs) are critical for their real-world deployment, particularly in ensuring accuracy, safety, and ethical alignment. Existing frameworks inadequately dissect domain-specific…

The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous…

Large Language Model (LLM) agents increasingly operate across domains such as robotics, virtual assistants, and web automation. However, their stochastic decision-making introduces safety risks that are difficult to anticipate during…

Recent advances in medical large language models (LLMs), multimodal models, and agents demand evaluation frameworks that reflect real clinical workflows and safety constraints. We present MedBench v4, a nationwide, cloud-based benchmarking…

Safety evaluations of memory-equipped LLM agents typically measure within-task safety: whether an agent completes a single scenario safely, often under adversarial conditions such as prompt injection or memory poisoning. In deployment,…

Vision-Language Models (VLMs) empower embodied agents to execute complex instructions, yet they remain vulnerable to contextual safety risks where benign commands become hazardous due to subtle environmental states. Existing safeguards…

While the safety risks of image-based large language models (Image LLMs) have been extensively studied, their video-based counterparts (Video LLMs) remain critically under-examined. To systematically study this problem, we introduce…

Hallucinations pose critical risks for large language model (LLM)-based agents, often manifesting as hallucinative actions resulting from fabricated or misinterpreted information within the cognitive context. While recent studies have…

With the rapid popularity of large language models such as ChatGPT and GPT-4, a growing amount of attention is paid to their safety concerns. These models may generate insulting and discriminatory content, reflect incorrect social values,…

Multimodal Large Reasoning Models (MLRMs) demonstrate impressive cross-modal reasoning but often amplify safety risks under adversarial or unsafe prompts, a phenomenon we call the \textit{Reasoning Tax}. Existing defenses mainly act at the…

The integration of large language models (LLMs) into robotic task planning has unlocked better reasoning capabilities for complex, long-horizon workflows. However, ensuring safety in LLM-driven plans remains a critical challenge, as these…

Recent advances in Vision-Language Models (VLMs) facilitate a new class of embodied AI systems, where these models are integrated into physical platforms, e.g. robots and autonomous vehicles, to interpret visual scenes and execute natural…

LLM-based agents have emerged as promising tools, which are crafted to fulfill complex tasks by iterative planning and action. However, these agents are susceptible to undesired planning hallucinations when lacking specific knowledge for…

While Large Language Models (LLMs) demonstrate significant potential in providing accessible mental health support, their practical deployment raises critical trustworthiness concerns due to the domains high-stakes and safety-sensitive…

As the capabilities of large language models (LLMs) continue to advance, the importance of rigorous safety evaluation is becoming increasingly evident. Recent concerns within the realm of safety assessment have highlighted instances in…

Large language model (LLM) agents are vulnerable to prompt-injection attacks that propagate through multi-step workflows, tool interactions, and persistent context, making input-output filtering alone insufficient for reliable protection.…