相关论文: Robust and Efficient Guardrails with Latent Reason…

Ensuring the safety of large language models (LLMs) is critical as they are deployed in real-world applications. Existing guardrails rely on rule-based filtering or single-pass classification, limiting their ability to handle nuanced safety…

Reasoning-based language models have demonstrated strong performance across various domains, with the most notable gains seen in mathematical and coding tasks. Recent research has shown that reasoning also offers significant benefits for…

As LLMs increasingly impact safety-critical applications, ensuring their safety using guardrails remains a key challenge. This paper proposes GuardReasoner, a new safeguard for LLMs, by guiding the guard model to learn to reason.…

Large Language Models (LLMs) are susceptible to adversarial attacks such as jailbreaking, which can elicit harmful or unsafe behaviors. This vulnerability is exacerbated in multilingual settings, where multilingual safety-aligned data is…

As large language models (LLMs) are increasingly deployed in real-world applications, safety guardrails are required to go beyond coarse-grained filtering and support fine-grained, interpretable, and adaptable risk assessment. However,…

As LLMs become increasingly prevalent across various applications, it is critical to establish safety guardrails to moderate input/output content of LLMs. Existing guardrail models treat various safety categories independently and fail to…

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…

Large Reasoning Models (LRMs) have demonstrated impressive performance in reasoning-intensive tasks, but they remain vulnerable to harmful content generation, particularly in the mid-to-late steps of their reasoning processes. Current…

Although the integration of large language models (LLMs) into robotics has unlocked transformative capabilities, it has also introduced significant safety concerns, ranging from average-case LLM errors (e.g., hallucinations) to adversarial…

Achieving robust safety alignment in large language models (LLMs) while preserving their utility remains a fundamental challenge. Existing approaches often struggle to balance comprehensive safety with fine-grained controllability at the…

The deployment of Large Reasoning Models (LRMs) in high-stakes decision-making pipelines has introduced a novel and opaque attack surface: reasoning backdoors. In these attacks, the model's intermediate Chain-of-Thought (CoT) is manipulated…

To enhance the safety of VLMs, this paper introduces a novel reasoning-based VLM guard model dubbed GuardReasoner-VL. The core idea is to incentivize the guard model to deliberatively reason before making moderation decisions via online RL.…

Guardrails are a critical safety layer for modern AI systems, but their operating regime is changing. As LLMs are deployed as customized assistants, safety policies are increasingly specified at inference time by users, organizations, or…

Large Language Models (LLMs) are typically aligned for safety during the post-training phase; however, they may still generate inappropriate outputs that could potentially pose risks to users. This challenge underscores the need for robust…

Large Reasoning Models (LRMs) leverage transparent reasoning traces, known as Chain-of-Thoughts (CoTs), to break down complex problems into intermediate steps and derive final answers. However, these reasoning traces introduce unique safety…

The rapid development of Multimodal Large Reasoning Models (MLRMs) has demonstrated broad application potential, yet their safety and reliability remain critical concerns that require systematic exploration. To address this gap, we conduct…

Recent reasoning-based safety guardrails for Large Reasoning Models (LRMs), such as deliberative alignment, have shown strong defense against jailbreak attacks. By leveraging LRMs' reasoning ability, these guardrails help the models to…

Large language models (LLMs) are increasingly embedded in Computer Science (CS) classrooms to automate code generation, feedback, and assessment. However, their susceptibility to adversarial or ill-intentioned prompts threatens student…

Large Language Models (LLMs) achieve superior performance through Chain-of-Thought (CoT) reasoning, but these token-level reasoning chains are computationally expensive and inefficient. In this paper, we introduce Compressed Latent…

The trend towards large language models (LLMs) for guardrailing against undesired behaviors is increasing and has shown promise for censoring user inputs. However, increased latency, memory consumption, hosting expenses and non-structured…