arXiv (All)
open access
From Latent Space to Jacobian Space: Measuring, Evading, and Training Against Safety-Content Accessibility
Output-only safety monitoring sees only the end of a model's computation, yet the model computes its answer before emitting it: what it is internally poised to say is safety-critical. Jacobian-space (J-space) readouts, linear maps from hidden states to the output vocabulary via the model's input-out
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- When Words Are Safe But Actions Kill: Probing Physical Danger Beyond Text Safety in Hidden-State Risk Space#373319
- Safety through Human Tracking in an Industrial Setting#398945
- Dual-Adversarial Safety Alignment: Cultivating Intrinsic Threat Comprehension in LRMs#441681
- Dyna-Style Safety Augmented Reinforcement Learning: Staying Safe in the Face of Uncertainty#141493
- Online Learning via Learned Latent Bayesian Tracking#1106258
Record · ID 1199967
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive