Adaptive multi-agent LLM pipelines with bandit-based sampling achieve lower false positive rates (0.095 vs 0.159) than single-agent models on two behavioral health datasets while maintaining similar false negative rates.
AEGIS2.0: A diverse AI safety dataset and risks taxonomy for alignment of LLM guardrails
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
representative citing papers
LPG compresses policy deliberation into 10 latent tokens to reach 84.5% safety accuracy and 11x speedup over explicit reasoning baselines on guardrail benchmarks.
GLiGuard is a compact schema-conditioned bidirectional encoder that matches 7B-27B guard models on safety benchmarks while delivering up to 16x higher throughput and 17x lower latency.
Annotator Policy Models learn safety policies from labeling behavior alone, accurately predicting responses and revealing sources of disagreement like policy ambiguity and value pluralism.
SIREN identifies safety neurons via linear probing on internal LLM layers and combines them with adaptive weighting to detect harm, outperforming prior guard models with 250x fewer parameters.
FRPO applies a max-min robust optimization over KL-bounded policy neighborhoods during RLHF to reduce catastrophic forgetting of safety and accuracy under subsequent SFT or RL fine-tuning.
Disentangled Safety Adapters decouple safety computations from task-optimized LLMs via lightweight adapters, yielding up to 53% better AUC on safety tasks and dynamic inference-time alignment with reduced performance trade-offs.
Opir introduces efficient multi-task encoder models trained on a 996-category safety taxonomy that match or exceed larger baselines on most safety benchmarks while using under 100M parameters for edge variants.
citing papers explorer
-
LLM Safety From Within: Detecting Harmful Content with Internal Representations
SIREN identifies safety neurons via linear probing on internal LLM layers and combines them with adaptive weighting to detect harm, outperforming prior guard models with 250x fewer parameters.