conftrace_

semantic safety

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) mirror crafting (1) entropy guidance (1) constitutions (1) injury reports (1) polytope (1) prompt calibration (1) adaptive defense (1) constitutional ai (1) visual scene (1)

Papers

MirrorShield: Towards Dynamic Adaptive Defense Against Jailbreaks via Entropy-Guided Mirror Crafting AAAI 2026 Generating Robot Constitutions & Benchmarks for Semantic Safety CoRL 2025 Learning Safety Constraints for Large Language Models ICML 2025