Related papers: Towards Inference-time Category-wise Safety Steeri…

Benefiting from the powerful capabilities of Large Language Models (LLMs), pre-trained visual encoder models connected to LLMs form Vision Language Models (VLMs). However, recent research shows that the visual modality in VLMs is highly…

Activation steering methods are widely used to control large language model (LLM) behavior and are often interpreted as revealing meaningful internal representations. This interpretation assumes that steering directions are identifiable and…

Having an LLM that aligns with human preferences is essential for accommodating individual needs, such as maintaining writing style or generating specific topics of interest. The majority of current alignment methods rely on fine-tuning or…

Studying the robustness of Large Language Models (LLMs) to unsafe behaviors is an important topic of research today. Building safety classification models or guard models, which are fine-tuned models for input/output safety classification…

Large Language Models (LLMs) encode vast amounts of parametric knowledge during pre-training. As world knowledge evolves, effective deployment increasingly depends on their ability to faithfully follow externally retrieved context. When…

Large Vision-Language Models face growing safety challenges with multimodal inputs. This paper introduces the concept of Implicit Reasoning Safety, a vulnerability in LVLMs. Benign combined inputs trigger unsafe LVLM outputs due to flawed…

In recent years, large language models (LLMs) have had great success in tasks such as casual conversation, contributing to significant advancements in domains like virtual assistance. However, they often generate responses that are not…

Multimodal large language models (MLLMs) are gaining increasing attention. Due to the heterogeneity of their input features, they face significant challenges in terms of jailbreak defenses. Current defense methods rely on costly fine-tuning…

Ensuring robust safety measures across a wide range of scenarios is crucial for user-facing systems. While Large Language Models (LLMs) can generate valuable data for safety measures, they often exhibit distributional biases, focusing on…

Large reasoning models (LRMs) achieved remarkable performance via chain-of-thought (CoT), but recent studies showed that such enhanced reasoning capabilities are at the expense of significantly degraded safety capabilities. In this paper,…

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…

Real-world autonomous driving must adhere to complex human social rules that extend beyond legally codified traffic regulations. Many of these semantic constraints, such as yielding to emergency vehicles, complying with traffic officers'…

Flight trajectory prediction is a critical time series task in aviation. While deep learning methods have shown significant promise, the application of large language models (LLMs) to this domain remains underexplored. This study pioneers…

Recent advancements in large language models (LLMs) have notably propelled natural language processing (NLP) capabilities, demonstrating significant potential in safety engineering applications. Despite these advancements, LLMs face…

The rapid development and deployment of large language models (LLMs) have introduced a new frontier in artificial intelligence, marked by unprecedented capabilities in natural language understanding and generation. However, the increasing…

Large Language Models (LLMs) are increasingly deployed for clinical reasoning tasks, which inherently require eliciting calibrated probabilistic beliefs based on available evidence. However, real-world clinical data are frequently…

Ensuring the safety and harmlessness of Large Language Models (LLMs) has become equally critical as their performance in applications. However, existing safety alignment methods typically suffer from safety-performance trade-offs and the…

Multi-modal Large Language Models (MLLMs) have achieved remarkable performance across a wide range of visual reasoning tasks, yet their vulnerability to safety risks remains a pressing concern. While prior research primarily focuses on…

It is a critical challenge to efficiently unlock the powerful reasoning potential of Large Language Models (LLMs) for specific tasks or new distributions. Existing test-time adaptation methods often require tuning model parameters, which is…

Large language models (LLMs) are useful tools with the capacity for performing specific types of knowledge work at an effective scale. However, LLM deployments in high-risk and safety-critical domains pose unique challenges, notably the…