arXiv AI September 18, 2026 By Alizishaan Khatri, Chiquita Prabhu, Omkar Neogi

Safety Beyond the Interface: Detecting Harm via Latent States in Large Language Models

The paper investigates whether large language models (LLMs) can internally detect harmful content, bypassing external guardrails that add latency and computational cost. By extracting activations from LLaMA‑3.1‑8B and training lightweight MLP probes, the authors achieve high F1 scores (99%, 83%, and 84%) on WildJailbreak, Beavertails, and AEGIS 2.0 benchmarks, rivaling much larger guard models while reducing overhead. This suggests that internal state monitoring can provide efficient safety checks for resource‑constrained, time‑critical deployments.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Jul 14

Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs

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.

By Jiayi Li, Kun Zhan

llms fine-tuning multimodal safety

arXiv AI

Jun 6

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack

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.

By Long P. Hoang, Hai V. Le, Shaoyang Xu, Wei Lu, Wenxuan Zhang

llms reinforcement-learning safety

arXiv AI

Aug 11

TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories

arXiv:2604. 07223v2 Announce Type: replace-cross Abstract: As large language models (LLMs) evolve from static chatbots into autonomous agents, the primary vulnerability surface shifts from final outputs to intermediate execution traces.

By Yen-Shan Chen, Sian-Yao Huang, Cheng-Lin Yang, Yun-Nung Chen

llms agents benchmarks safety

Hugging Face Trending Papers

Jun 4

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack

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.

llms reinforcement-learning safety

arXiv Computation and Language

Aug 25

No One Model Catches Every Harm: Benchmarking Content Moderation Across Safety Scenarios

arXiv:2608.21775v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in real-world applications, yet they remain vulnerable to generating harmful content. From adver...

By Afshin Orojlooyjadid, Hitesh Patel

llms benchmarks safety

arXiv AI

Jul 3

kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail

arXiv:2607. 02072v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in domains requiring guardrails to detect unsafe, off-topic, or adversarial prompts.

By Mahmoud Abdelfattah, Hamid Nasiri, Peter Garraghan

llms rag fine-tuning efficiency benchmarks safety

One email a morning, machine-written

Related stories

Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack

TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack

No One Model Catches Every Harm: Benchmarking Content Moderation Across Safety Scenarios

kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail