相关论文: Safety Geometry Collapse in Multimodal LLMs and Ad…

Large language models confidently produce outdated answers, and no existing method can detect them. We show this is not an engineering failure but a structural one: temporal drift, whether a stored fact has changed since training, is…

This study addresses a critical gap in safety tuning practices for Large Language Models (LLMs) by identifying and tackling a refusal position bias within safety tuning data, which compromises the models' ability to appropriately refuse…

Large Vision-Language Models (LVLMs) have transformed multi-modal understanding, excelling in tasks like image captioning and visual question answering by integrating visual and textual inputs. However, their robustness against adversarial…

Refusal refers to the functional behavior enabling safety-aligned language models to reject harmful or unethical prompts. Following the growing scientific interest in mechanistic interpretability, recent work encoded refusal behavior as a…

This study addresses construction site hazard identification by proposing a retrieval-augmented framework that enhances large language models (LLMs) without requiring fine-tuning. Current LLM-based approaches face limitations: image-text…

Large Language Models (LLMs) increasingly rely on multi-turn reasoning and interaction, such as adaptive retrieval-augmented generation (RAG) and ReAct-style agents, to answer difficult questions. These methods improve accuracy by…

Vision and language models (VL) are known to exploit unrobust indicators in individual modalities (e.g., introduced by distributional biases) instead of focusing on relevant information in each modality. That a unimodal model achieves…

LLMs increasingly exhibit over-refusal behavior, where safety mechanisms cause models to reject benign instructions that seemingly resemble harmful content. This phenomenon diminishes utility in production applications that repeatedly rely…

Multimodal large language models (MLLMs) are essential for building general-purpose AI assistants; however, they pose increasing safety risks. How can we ensure safety alignment of MLLMs to prevent undesired behaviors? Going further, it is…

Multimodal large language models (MLLMs) have shown satisfactory effects in many autonomous driving tasks. In this paper, MLLMs are utilized to solve joint semantic scene understanding and risk localization tasks, while only relying on…

Human cognition, driven by complex neurochemical processes, oscillates between imagination and reality and learns to self-correct whenever such subtle drifts lead to hallucinations or unsafe associations. In recent years, LLMs have…

Multimodal Large Language Models demonstrate strong performance on multimodal benchmarks, yet often exhibit poor robustness when exposed to spurious modality interference, such as irrelevant text in vision understanding, or irrelevant…

Large Language Models (LLMs) rely on safety alignment to produce socially acceptable responses. However, this behavior is known to be brittle: further fine-tuning, even on benign or lightly contaminated data, can degrade safety and…

Fine-tuning large language models (LLMs) on additional datasets is often necessary to optimize them for specific downstream tasks. However, existing safety alignment measures, which restrict harmful behavior during inference, are…

The emergence of Large Reasoning Models (LRMs) introduces a new paradigm of explicit reasoning, enabling remarkable advances yet posing unique risks such as reasoning manipulation and information leakage. To mitigate these risks, current…

Traffic safety remains a critical global challenge, with traditional Advanced Driver-Assistance Systems (ADAS) often struggling in dynamic real-world scenarios due to fragmented sensor processing and susceptibility to adversarial…

Large Vision-Language Models (LVLMs) have made significant strides in multimodal comprehension, thanks to extensive pre-training and fine-tuning on large-scale visual datasets. However, despite their robust textual safety mechanisms, they…

Integrating large language model (LLM) representations into multimodal recommendation has shown promise, yet a fundamental challenge remains largely overlooked: the semantic heterogeneity between generative LM representations and the…

Safety alignment has become a critical step to ensure LLMs refuse harmful requests while providing helpful and harmless responses. However, despite the ubiquity of safety alignment for deployed frontier models, two separate lines of recent…

Multimodal large language models (MLLMs) have achieved remarkable progress across a range of vision-language tasks and demonstrate strong potential for traffic accident understanding. However, existing MLLMs in this domain primarily focus…