Safety · Concept
ConceptGuard: Context-Sensitive Concept-Level LLM Unlearning Benchmark
Benchmark of dual-use concepts requiring removal of harmful uses while retaining benign conceptual competence.
Forecast horizon
Connections
Connections · 3
How this node ties into the rest of the map, and the evidence behind each link.
to · standardizes 4/10
LLM Unlearning via Representation Selectivity (RepSelect) ConceptGuard reframes unlearning evaluation around dual-use concepts rather than disjoint factual forget/retain sets.
+4 growth to · frames 3/10
LLM Unlearning via Representation Selectivity (RepSelect) ConceptGuard reframes unlearning evaluation around dual-use concepts rather than disjoint fact sets.
+3 growth from · references 3/10
arXiv LLM Agents Submissions (Aug 2026 batch) August arXiv agents batch introduces ConceptGuard for context-sensitive concept-level unlearning.
+3 growthSignal sources
Signal sources
Dated facts from primary sources in this direction.
US evaluation centre Jun 2025
In June 2025 the US AI Safety Institute was renamed the Center for AI Standards and Innovation (CAISI), pivoting toward security, standards and adversary-model assessment.
NIST → Frontier safeguards May 2025
Anthropic activated its ASL-3 deployment and security standard with Claude Opus 4 on 22 May 2025 — the first real-world trigger of a responsible-scaling tier, focused on blocking bio-weapon uplift.
Anthropic → Cross-border testing 2025
The International Network of AI Safety Institutes (launched Nov 2024) ran a third joint testing exercise focused on agentic AI systems across cyber and fraud strands.
European Commission — AI Office →