相关论文: Refusal Falls off a Cliff: How Safety Alignment Fa…

With the rapid advancement of large language models (LLMs), the safety of LLMs has become a critical concern. Despite significant efforts in safety alignment, current LLMs remain vulnerable to jailbreaking attacks. However, the root causes…

Large reasoning models (LRMs) generate chain-of-thought (CoT) traces before producing final outputs, introducing a dynamic internal state that may complicate control mechanisms such as refusal. Unlike instruction-tuned LLMs, where refusal…

Large Language Models (LLMs) have demonstrated remarkable success across various NLP benchmarks. However, excelling in complex tasks that require nuanced reasoning and precise decision-making demands more than raw language proficiency--LLMs…

Reasoning Large Language Models (LLMs) enable test-time scaling, with dataset-level accuracy improving as the token budget increases, motivating adaptive reasoning -- spending tokens when they improve reliability and stopping early when…

Large language models increasingly rely on explicit chain-of-thought reasoning to solve complex tasks, yet the safety of the reasoning process itself remains largely unaddressed. Existing work focuses predominantly on content safety (i.e.,…

From the perspective of content safety issues, alignment has shown to limit large language models' (LLMs) harmful content generation. This intentional method of reinforcing models to not respond to certain user inputs seem to be present in…

Reinforcement learning (RL) plays a crucial role in shaping the behavior of large language and reasoning models (LLMs/LRMs). However, it often produces brittle and unstable policies, leading to critical failures such as spurious reasoning,…

Reasoning language models (RLMs) achieve strong performance on complex reasoning tasks, yet they still exhibit a multilingual reasoning gap, performing better in high-resource languages than in low-resource ones. While recent efforts have…

Instruction-following is essential for aligning large language models (LLMs) with user intent. While recent reasoning-oriented models exhibit impressive performance on complex mathematical problems, their ability to adhere to natural…

Large Reasoning Models (LRMs) achieve strong performance on complex multi-step reasoning, yet they still exhibit severe safety failures such as harmful content generation. Existing methods often apply coarse-grained constraints over the…

Large Reasoning Models possess remarkable capabilities for self-correction in general domain; however, they frequently struggle to recover from unsafe reasoning trajectories under adversarial attacks. Existing alignment methods attempt to…

Large Language Models (LLMs) excel in reasoning tasks requiring a single correct answer, but they perform poorly in multi-solution tasks that require generating comprehensive and diverse answers. We attribute this limitation to…

Large language models (LLMs) possess strong semantic understanding, driving significant progress in data mining applications. This is further enhanced by large reasoning models (LRMs), which provide explicit multi-step reasoning traces. On…

Automated \enquote{LLM-as-a-Judge} frameworks have become the de facto standard for scalable evaluation across natural language processing. For instance, in safety evaluation, these judges are relied upon to evaluate harmfulness in order to…

Large language models (LLMs) excel in various capabilities but pose safety risks such as generating harmful content and misinformation, even after safety alignment. In this paper, we explore the inner mechanisms of safety alignment through…

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…

Vision-Language Models (VLMs) have achieved remarkable progress in multimodal reasoning tasks through enhanced chain-of-thought capabilities. However, this advancement also introduces novel safety risks, as these models become increasingly…

Large Reasoning Models (LRMs), such as OpenAI o1 and DeepSeek-R1, have been rapidly progressing and achieving breakthrough performance on complex reasoning tasks such as mathematics and coding. However, the open-source R1 models have raised…

For Large Language Models (LLMs) to be reliably deployed in both everyday and high-stakes domains, knowing when not to answer is equally critical as answering correctly. Real-world user queries, which can be underspecified, ill-posed, or…

Large language models (LLMs) have shown significant progress in reasoning tasks. However, recent studies show that transformers and LLMs fail catastrophically once reasoning problems exceed modest complexity. We revisit these findings…