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.
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.
AdaGuard is an adaptive guard model that evaluates language‑model agent trajectories against user‑defined policies. The authors created the AdaptiveSafety dataset, containing 10,939 training and 1,000 test examples with policy rules, counterfactuals, explanations, and violated rules. Using supervised pre‑training followed by the SafePO reinforcement‑learning algorithm, they built 0.6B, 4B, and 8B guard models, with the 4B version achieving 89.30% accuracy on AdaptiveSafety and 71.82% on DynaBench.
Large language models increasingly stream long, reasoning-intensive responses in real time, making when to moderate as critical as whether to moderate. Existing guardrails fall into two unsatisfactory extremes: response-level methods delay intervention until the full output is generated, whereas token-level methods act on incomplete semantics, often producing unstable decisions and excessive guard invocations.
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.
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.
The paper introduces a framework for evaluating AI systems that not only checks final labels but also tracks the reasoning behind them through three core sources—grounds, norms, and authority—forming an eight-cell counterfactual judgment cube. It defines minimal source replacement sets, called judgment receipts, to explain changes in verdicts and provides certification cost bounds for black-box evaluators. The authors present ReasonBench, a benchmark with 19,520 cases, and demonstrate that while high standard accuracy can mask robustness issues, receipt accuracy reveals significant gaps in reasoning consistency across different models.
The paper evaluates safety monitors by measuring recall only on prompts that the target model actually answers, rather than on all harmful prompts. Across several guard systems, recall at a 1% false‑positive rate drops sharply when focusing on answered prompts, with monitors catching refused requests 1.1–6.4 times more often than answered ones. Rewriting prompts to be less explicit dramatically increases compliance and reveals that many harmful requests slip past monitors, especially when phrasing is softened. Fine‑tuning guards on these rewritten prompts improves recall from 0.24 to 0.89 on answered requests and generalizes to unseen benchmarks.
arXiv:2609.06540v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in safety-critical applications, yet jailbreak attacks can conceal harmful intent through role...
arXiv:2610.07532v1 Announce Type: cross Abstract: LLMs have advanced rapidly, raising growing concerns about their safety. Recent work has proposed approaches to detect and defend against attacks inc...
arXiv:2607. 06326v1 Announce Type: new Abstract: Large language models deployed in open-world applications require safety guardrails that are both robust to complex risks and efficient enough for low-latency runtime moderation.
arXiv:2610.16814v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as judges to assign scalar scores that drive downstream decision-making, including tasks such as p...