arXiv:2606. 16808v1 Announce Type: new Abstract: While Large Reasoning Models (LRMs) excel at complex tasks, they remain highly vulnerable to sophisticated jailbreaks and direct harmful queries.
arXiv:2606. 05614v1 Announce Type: new Abstract: Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content.
The paper investigates why large reasoning models (LRMs) lose safety alignment when faced with harmful queries. By analyzing token-level refusal dynamics, the authors identify a vulnerability called Onset Refusal Collapse (ORC), where the refusal signal drops sharply at the first generated token, leading to unsafe responses. They introduce SafeToken, a lightweight inference-time intervention that injects a learned safety anchor at reasoning onset, which mitigates ORC, improves safety on harmful-query benchmarks, and largely preserves reasoning utility.
Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content. In this work, we reveal that this advanced safety awareness inadvertently introduces a fatal vulnerability.
arXiv:2603. 07445v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often require fine-tuning (FT) to perform well on downstream tasks, but FT can induce safety-alignment drift even when the training dataset contains only benign data.
arXiv:2511. 21214v4 Announce Type: replace-cross Abstract: Explicit safety policies can improve reasoning-model safety, but their effective coverage may lag behind evolving jailbreak strategies.
arXiv:2506. 07031v5 Announce Type: replace-cross Abstract: Emerging Large Reasoning Models (LRMs) consistently excel in mathematical and reasoning tasks, showcasing remarkable capabilities.
arXiv:2609.37054v2 Announce Type: replace Abstract: Ensuring the safety of reasoning large language models (LLMs) across languages is essential for their reliable deployment. However, when exposed to...
arXiv:2609.37054v1 Announce Type: new Abstract: Ensuring the safety of reasoning large language models (LLMs) across languages is essential for their reliable deployment. However, when exposed to jai...
The paper introduces COLAGUARD, a guardrail model that embeds multi-step safety reasoning into a continuous latent space, allowing efficient hidden-state propagation during inference. Compared to existing methods, COLAGUARD achieves an 8.24‑point macro‑F1 improvement over Llama Guard 3 and matches the explicit reasoning baseline GuardReasoner, while delivering a 12.9× speedup and a 22.4× reduction in token usage across ten moderation settings and eight safety benchmarks.
The paper introduces "cunning questions"—non‑safety prompts that contain misleading premises or subtle inconsistencies—to train large language models (LLMs) to scrutinize underlying intent and assumptions. Experiments show that incorporating these questions improves robustness against out‑of‑distribution jailbreak attacks and enhances subsequent safety fine‑tuning, achieving a new state‑of‑the‑art reduction in mean ASR from 17.40% to 15.05% across nine backbone–benchmark combinations. The authors argue that this training fosters vigilance, enabling models to prioritize safety judgments before engaging in harmful planning.
TRACE is a new benchmark that evaluates the safety of Large Reasoning Models (LRMs) across the entire inference pipeline, including prompts, reasoning traces, and final responses. It provides prompts in two languages covering nine risk categories and ten attack strategies, and for each prompt four LRMs generate traces and responses that are annotated for safety with supporting evidence extracted from the source text. Evaluation of 18 guardrail models on TRACE shows that detecting unsafe content in reasoning traces is much harder than in prompts or final responses, and that current models struggle to extract the necessary evidence.
arXiv:2607. 09697v1 Announce Type: new Abstract: Existing safety mechanisms for multimodal large language models (MLLMs) face a fundamental trade-off between safety and utility.