相关论文: AM$^3$Safety: Towards Data Efficient Alignment of …

The robust safety of Vision-Language Large Models (VLLMs) against joint multilingual and multimodal threats remains severely underexplored. Current benchmarks typically isolate these dimensions, being either multilingual but text-only, or…

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…

Multimodal large language models (MLLMs) have demonstrated impressive reasoning and instruction-following capabilities, yet their expanded modality space introduces new compositional safety risks that emerge from complex text-image…

With the development of large language models (LLMs), striking a balance between the performance and safety of AI systems has never been more critical. However, the inherent tension between the objectives of helpfulness and harmlessness…

Current vision large language models (VLLMs) exhibit remarkable capabilities yet are prone to generate harmful content and are vulnerable to even the simplest jailbreaking attacks. Our initial analysis finds that this is due to the presence…

Existing approaches to language model alignment often treat safety as a tradeoff against helpfulness, which can lead to unacceptable responses in sensitive domains. To ensure reliable performance in such settings, we propose High-Confidence…

The proliferation of jailbreak attacks against large language models (LLMs) highlights the need for robust security measures. However, in multi-round dialogues, malicious intentions may be hidden in interactions, leading LLMs to be more…

While safety alignment for Multimodal Large Language Models (MLLMs) has gained significant attention, current paradigms primarily target malicious intent or situational violations. We propose shifting the safety frontier toward…

Safety alignment in large language models (LLMs) is primarily evaluated under open-ended generation, where models can mitigate risk by refusing to respond. In contrast, many real-world applications place LLMs in structured decision-making…

Large Language Models (LLMs) have revolutionized conversational AI, yet their robustness in extended multi-turn dialogues remains poorly understood. Existing evaluation frameworks focus on static benchmarks and single-turn assessments,…

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…

Multimodal large language models (MLLMs) have shown impressive reasoning abilities. However, they are also more vulnerable to jailbreak attacks than their LLM predecessors. Although still capable of detecting the unsafe responses, we…

Multimodal Large Language Models (MLLMs) are rapidly evolving, demonstrating impressive capabilities as multimodal assistants that interact with both humans and their environments. However, this increased sophistication introduces…

Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation…

Large Multimodal Models (LMMs) have demonstrated the ability to interact with humans under real-world conditions by combining Large Language Models (LLMs) and modality encoders to align multimodal information (visual and auditory) with…

Multimodal large language models (MLLMs) face safety misalignment, where visual inputs enable harmful outputs. To address this, existing methods require explicit safety labels or contrastive data; yet, threat-related concepts are concrete…

Multimodal Large Language Models (MLLMs) have expanded the capabilities of traditional language models by enabling interaction through both text and images. However, ensuring the safety of these models remains a significant challenge,…

Despite notable advancements in Multimodal Large Language Models (MLLMs), most state-of-the-art models have not undergone thorough alignment with human preferences. This gap exists because current alignment research has primarily achieved…

In this study, we introduce the safety human preference dataset, PKU-SafeRLHF, designed to promote research on safety alignment in large language models (LLMs). As a sibling project to SafeRLHF and BeaverTails, we separate annotations of…

Language Model Models (LLMs) have improved dramatically in the past few years, increasing their adoption and the scope of their capabilities over time. A significant amount of work is dedicated to ``model alignment'', i.e., preventing LLMs…