相关论文: Consistent but Dangerous: Per-Sample Safety Classi…

Although large language models (LLMs) achieve effective safety alignment at the time of release, they still face various safety challenges. A key issue is that fine-tuning often compromises the safety alignment of LLMs. To address this…

With the rapid development of large language models (LLMs), they are not only used as general-purpose AI assistants but are also customized through further fine-tuning to meet the requirements of different applications. A pivotal factor in…

Larger language models (LLMs) have taken the world by storm with their massive multi-tasking capabilities simply by optimizing over a next-word prediction objective. With the emergence of their properties and encoded knowledge, the risk of…

Advancements in Large Vision-Language Models (LVLMs) have demonstrated promising performance in a variety of vision-language tasks involving image-conditioned free-form text generation. However, growing concerns about hallucinations in…

As Multimodal Large Language Models (MLLMs) acquire stronger reasoning capabilities to handle complex, multi-image instructions, this advancement may pose new safety risks. We study this problem by introducing MIR-SafetyBench, the first…

Traditional benchmarks for large language models (LLMs), such as HELM and AIR-BENCH, primarily assess safety risk through breadth-oriented evaluation across diverse tasks. However, real-world deployment often exposes a different class of…

Large vision-language models (LVLMs) have achieved remarkable progress in vision-language reasoning tasks, yet ensuring their safety remains a critical challenge. Recent input-side defenses detect unsafe images with CLIP and prepend safety…

Large Language Model (LLM) safety is inherently pluralistic, reflecting variations in moral norms, cultural expectations, and demographic contexts. Yet, existing alignment datasets such as ANTHROPIC-HH and DICES rely on demographically…

Background Large language models (LLMs) are increasingly deployed in medical consultations, yet their safety under realistic user pressures remains understudied. Prior assessments focused on neutral conditions, overlooking vulnerabilities…

Large language models have been shown to behave inconsistently in response to meaning-preserving paraphrastic inputs. At the same time, researchers evaluate the knowledge and reasoning abilities of these models with test evaluations that do…

Large language models (LLMs) have emerged as powerful tools for addressing a wide range of general inquiries and tasks. Despite this, fine-tuning aligned LLMs on smaller, domain-specific datasets, critical to adapting them to specialized…

Multi-modal large language models (MLLMs) have made significant progress, yet their safety alignment remains limited. Typically, current open-source MLLMs rely on the alignment inherited from their language module to avoid harmful…

With the integration of an additional modality, large vision-language models (LVLMs) exhibit greater vulnerability to safety risks (e.g., jailbreaking) compared to their language-only predecessors. Although recent studies have devoted…

The robustness of Vision Language Models (VLMs) is commonly assessed through output-level invariance, implicitly assuming that stable predictions reflect stable multimodal processing. In this work, we argue that this assumption is…

Vision-Language Models (VLMs) are now a core part of modern AI. Recent work proposed several visual jailbreak attacks using single/ holistic images. However, contemporary VLMs demonstrate strong robustness against such attacks due to…

Vision-Language Models (VLMs) achieve strong cross-modal performance, yet recent evidence suggests they over-rely on textual descriptions while under-utilizing visual evidence -- a phenomenon termed ``text shortcut learning.'' We propose an…

Large language models (LLMs) are increasingly used for high-stakes decisions, yet their susceptibility to spurious features remains poorly characterized. We introduce ICE-Guard, a framework applying intervention consistency testing to…

Large language models used for clinical abstraction are sensitive to prompt wording, yet most work treats prompts as fixed and studies uncertainty in isolation. We argue these should be treated jointly. Across two clinical tasks (MedAlign…

Vision-Language Models (VLMs) are powerful yet computationally intensive for widespread practical deployments. To address such challenge without costly re-training, post-training acceleration techniques like quantization and token reduction…

Vision-language-action models (VLAs) show potential as generalist robot policies. However, these models pose extreme safety challenges during real-world deployment, including the risk of harm to the environment, the robot itself, and…