相关论文: UnsafeChain: Enhancing Reasoning Model Safety via …

Recent advances in test-time scaling have enabled Large Language Models (LLMs) to display sophisticated reasoning abilities via extended Chain-of-Thought (CoT) generation. Despite their potential, these Reasoning LLMs (RLMs) often…

Many studies have demonstrated that large language models (LLMs) can produce harmful responses, exposing users to unexpected risks when LLMs are deployed. Previous studies have proposed comprehensive taxonomies of the risks posed by LLMs,…

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 Language Models (LLMs) are increasingly adopted in high-stakes scenarios, yet their safety mechanisms often remain fragile. Simple jailbreak prompts or even benign fine-tuning can bypass these protocols, underscoring the need to…

Large Reasoning Models (LRMs) achieve remarkable success through explicit thinking steps, yet the thinking steps introduce a novel risk by potentially amplifying unsafe behaviors. Despite this vulnerability, conventional defense mechanisms…

We discover a novel and surprising phenomenon of unintentional misalignment in reasoning language models (RLMs), which we call self-jailbreaking. Specifically, after benign reasoning training on math or code domains, RLMs will use multiple…

Reinforcement learning (RL) based post-training for explicit chain-of-thought (e.g., GRPO) improves the reasoning ability of multimodal large-scale reasoning models (MLRMs). But recent evidence shows that it can simultaneously degrade…

While Multimodal Large Language Models (MLLMs) have made remarkable progress in vision-language reasoning, they are also more susceptible to producing harmful content compared to models that focus solely on text. Existing defensive…

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.…

LLMs(Large Language Models) nowadays have widespread adoption as a tool for solving issues across various domain/tasks. These models since are susceptible to produce harmful or toxic results, inference-time adversarial attacks, therefore…

Large Reasoning Models (LRMs) have advanced automated multi-step reasoning, but their ability to generate complex Chain-of-Thought (CoT) trajectories introduces severe privacy risks, as sensitive information may be deeply embedded…

The rapid advancement of large language models (LLMs) has driven their adoption across diverse domains, yet their ability to generate harmful content poses significant safety challenges. While extensive research has focused on mitigating…

Large Language Models (LLMs) have demonstrated powerful capabilities that render them valuable in different applications, including conversational AI products. It is paramount to ensure the security and reliability of these products by…

Large Language Models (LLMs) trained via Reinforcement Learning (RL) have recently achieved impressive results on reasoning benchmarks. Yet, growing evidence shows that these models often generate longer but ineffective chains of thought…

Large language models (LLMs) have become ubiquitous, interfacing with humans in numerous safety-critical applications. This necessitates improving capabilities, but importantly coupled with greater safety measures to align these models with…

Recent advancements in Chain-of-Thought (CoT) reasoning utilize complex modules but are hampered by high token consumption, limited applicability, and challenges in reproducibility. This paper conducts a critical evaluation of CoT…

Unsafe prompts pose significant safety risks to large language models (LLMs). Existing methods for detecting unsafe prompts rely on data-driven fine-tuning to train guardrail models, necessitating significant data and computational…

Large language models (LLMs) have shown impressive capabilities in handling complex tasks through long-chain reasoning. However, the extensive reasoning steps involved can significantly increase computational costs, posing challenges for…

The development of Long-CoT reasoning has advanced LLM performance across various tasks, including language understanding, complex problem solving, and code generation. This paradigm enables models to generate intermediate reasoning steps,…

The increasing sophistication of large vision-language models (LVLMs) has been accompanied by advances in safety alignment mechanisms designed to prevent harmful content generation. However, these defenses remain vulnerable to sophisticated…