Related papers: UnsafeChain: Enhancing Reasoning Model Safety via …

Existing safety assurance research has primarily focused on training-phase alignment to instill safe behaviors into LLMs. However, recent studies have exposed these methods' susceptibility to diverse jailbreak attacks. Concurrently,…

We present InvThink, a training and prompting framework that requires the model to enumerate, analyze, and constrain potential failures before generating its final response. Unlike existing safety alignment methods that optimize only for…

The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. These advanced reasoning capabilities provide new avenues for improving the safety and robustness of our models. In particular, our…

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…

Multimodal large reasoning models (MLRMs) are increasingly deployed for vision-language tasks that produce explicit intermediate rationales. However, reasoning traces can contain unsafe content even when the final answer is non-harmful,…

Large Reasoning Models (LRMs) have emerged as a powerful advancement in multi-step reasoning tasks, offering enhanced transparency and logical consistency through explicit chains of thought (CoT). However, these models introduce novel…

Large Language Models (LLMs) have been demonstrating strong reasoning capability with their chain-of-thoughts (CoT), which are routinely used by humans to judge answer quality. This reliance creates a powerful yet fragile basis for trust.…

Chain-of-Thought (CoT) prompting has become the de facto method to elicit reasoning capabilities from large language models (LLMs). However, to mitigate hallucinations in CoT that are notoriously difficult to detect, current methods such as…

This paper investigates an under-explored challenge in large language models (LLMs): chain-of-thought prompting with noisy rationales, which include irrelevant or inaccurate reasoning thoughts within examples used for in-context learning.…

Most flagship language models generate explicit reasoning chains, enabling inference-time scaling. However, producing these reasoning chains increases token usage (i.e., reasoning tokens), which in turn increases latency and costs. Our…

Scaling inference compute enhances reasoning in large language models (LLMs), with long chains-of-thought (CoTs) enabling strategies like backtracking and error correction. Reinforcement learning (RL) has emerged as a crucial method for…

While the wide adoption of refusal training in large language models (LLMs) has showcased improvements in model safety, recent works have highlighted shortcomings due to the shallow nature of these alignment methods. To this end, the work…

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…

Chain-of-Thought (CoT) reasoning enables Large Language Models (LLMs) to solve complex reasoning tasks by generating intermediate reasoning steps. However, most existing approaches focus on hard token decoding, which constrains reasoning…

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…

While there has been progress towards aligning Large Language Models (LLMs) with human values and ensuring safe behaviour at inference time, safety guards can easily be removed when fine tuned on unsafe and harmful datasets. While this…

The ability of large language models (LLMs) to follow user instructions is central to their reliability, safety, and usefulness. While prior studies assess instruction adherence in the model's main responses, we argue that it is also…

Chain of Thought (CoT) is significant in improving the reasoning abilities of large language models (LLMs). However, the correlation between the effectiveness of CoT and the length of reasoning steps in prompts remains largely unknown. To…

Without proper safeguards, large language models will readily follow malicious instructions and generate toxic content. This risk motivates safety efforts such as red-teaming and large-scale feedback learning, which aim to make models both…

Ensuring the safety and harmlessness of Large Language Models (LLMs) has become equally critical as their performance in applications. However, existing safety alignment methods typically suffer from safety-performance trade-offs and the…