Related papers: Reasoning Structure Matters for Safety Alignment o…

Large reasoning models (LRMs) extend large language models by generating explicit chain-of-thought (CoT) reasoning, significantly improving mathematical and logical problem solving. However, this explicit reasoning process also introduces…

Large Reasoning Models (LRMs) have achieved remarkable success on reasoning-intensive tasks such as mathematics and programming. However, their enhanced reasoning capabilities do not necessarily translate to improved safety performance-and…

Despite the impressive performance of general-purpose large language models (LLMs), they often require fine-tuning or post-training to excel at specific tasks. For instance, large reasoning models (LRMs), such as the DeepSeek-R1 series,…

Safety alignment is an important procedure before the official deployment of a Large Language Model (LLM). While safety alignment has been extensively studied for LLM, there is still a large research gap for Large Reasoning Models (LRMs)…

Large reasoning models (LRMs) "think" by generating structured chain-of-thought (CoT) before producing a final answer, yet they still lack the ability to reason critically about safety alignment and are easily biased when a flawed premise…

Current safety alignment techniques for large language models (LLMs) face two key challenges: (1) under-generalization, which leaves models vulnerable to novel jailbreak attacks, and (2) over-alignment, which leads to the excessive refusal…

Large Reasoning Models (LRMs) have significantly improved problem-solving through explicit Chain-of-Thought (CoT) reasoning. However, this capability creates a Safety-Helpfulness Paradox: the reasoning process itself can be misused to…

Large reasoning models (LRMs) achieved remarkable performance via chain-of-thought (CoT), but recent studies showed that such enhanced reasoning capabilities are at the expense of significantly degraded safety capabilities. In this paper,…

Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit weaknesses in traditional safety alignment, which often relies on rigid refusal heuristics or representation engineering to block harmful outputs. While they are…

Reasoning-capable LLMs have achieved major breakthroughs in solving complex problems, but recent work shows that acquiring and deploying strong reasoning can introduce significant safety risks. A common mitigation is to apply a secondary…

Although large reasoning models (LRMs) have demonstrated impressive capabilities on complex tasks, recent studies reveal that these models frequently fulfill harmful user instructions, raising significant safety concerns. In this paper, we…

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 methods that adaptively allocate test-time compute have advanced LLM performance on easy to verify domains such as math and code. In this work, we study how to utilize this approach to train models that exhibit a degree of…

Emerging large reasoning models (LRMs), such as DeepSeek-R1 models, leverage long chain-of-thought (CoT) reasoning to generate structured intermediate steps, enhancing their reasoning capabilities. However, long CoT does not inherently…

Large language models (LLMs), despite possessing latent safety understanding from their vast pretraining data, remain vulnerable to generating harmful content and exhibit issues such as over-refusal and utility degradation after 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…

Large Reasoning Models (LRMs) have exhibited extraordinary prowess in tasks like mathematics and coding, leveraging their advanced reasoning capabilities. Nevertheless, as these capabilities progress, significant concerns regarding their…

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 Reasoning Models (LRMs) have become powerful tools for complex problem solving, but their structured reasoning pathways can lead to unsafe outputs when exposed to harmful prompts. Existing safety alignment methods reduce harmful…

As large reasoning models (LRMs) grow more capable, chain-of-thought (CoT) reasoning introduces new safety challenges. Existing SFT-based safety alignment studies dominantly focused on filtering prompts with safe, high-quality responses,…