Local linearity of LLM layers enables LQR-based closed-loop activation steering with theoretical tracking guarantees.
Advances in Neural Information Processing Systems , volume=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
STAR-Teaming uses a Strategy-Response Multiplex Network inside a multi-agent framework to organize attack strategies into semantic communities, delivering higher attack success rates on LLMs at lower computational cost than prior methods.
Changing the internal reasoning structure of large reasoning models through simple supervised fine-tuning on 1K examples produces strong safety alignment that generalizes across tasks and languages.
SafeHarbor introduces a hierarchical memory-augmented guardrail with adversarial rule extraction and entropy-driven self-evolution to balance safety and utility in LLM agents.
citing papers explorer
-
Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control
Local linearity of LLM layers enables LQR-based closed-loop activation steering with theoretical tracking guarantees.
-
STAR-Teaming: A Strategy-Response Multiplex Network Approach to Automated LLM Red Teaming
STAR-Teaming uses a Strategy-Response Multiplex Network inside a multi-agent framework to organize attack strategies into semantic communities, delivering higher attack success rates on LLMs at lower computational cost than prior methods.
-
Reasoning Structure Matters for Safety Alignment of Reasoning Models
Changing the internal reasoning structure of large reasoning models through simple supervised fine-tuning on 1K examples produces strong safety alignment that generalizes across tasks and languages.
-
SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
SafeHarbor introduces a hierarchical memory-augmented guardrail with adversarial rule extraction and entropy-driven self-evolution to balance safety and utility in LLM agents.