arXiv AI
LongGuard: Mechanistic Analysis and Training-Free Mitigation of Long-Context Failure in Safety Guardrails
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 7
Robust and Efficient Guardrails with Latent Reasoning
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.
arXiv AI
Oct 28
Follow the Gradient: Tracing Safety Degradation Back to Training Data
The paper introduces SimpleLoRIF, a scalable gradient‑embedding technique that pinpoints fine‑tuning examples whose gradients align with unsafe behavior in large language models. By applying this method, the authors create SafeTulu, a version of Tulu 3 with the 20 % of most unsafe‑aligned examples removed, which reduces GCG attack success by up to 22 % across several LLMs while largely preserving or improving capability. The study also highlights previously under‑studied safety‑degrading data sources such as tool‑execution failures and narrative arithmetic.
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.
arXiv AI
Oct 23
AdaGuard: An Adaptive Guard Model with User-defined Policies
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.
arXiv Machine Learning
Jul 14
HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models
arXiv:2607. 11475v1 Announce Type: new Abstract: Safety alignment in large language models can be fragile under fine-tuning, as even benign task adaptation may increase harmful compliance.
arXiv Computation and Language
Oct 26
Omni-UBench: Benchmarking Omni-Modal LLM-based Guardrails Across Safety, Utility, and Reliability
arXiv:2610.31713v1 Announce Type: cross Abstract: Advances in Omni-modal Large Language Models (OLLMs) have enabled increasingly seamless human-AI interaction, but their unified processing of heterog...