arXiv (All)
open access
TIER: Threat Implicitness Benchmark for Evaluating LLM Safety Behaviors
Current LLM safety benchmarks largely rely on binary metrics, overlooking how models respond to harmful prompts with varying threat implicitness. We introduce TIER, a Threat Implicitness Benchmark for behavioral safety evaluation of LLMs. TIER covers four risk domains and four threat levels, from ex
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
- Testing the Constraint Engine: Adversarial Self-Interrogation of Consciousness Architecture Claims#111936
- A Multiverse of Good and Bad Controls: Candidate Causal Graphs for Interpreting Model Robustness Analysis#1122636
- Off the Rails: Hijacking the Scoring Head in Generative End-to-End Driving Planners with Safety-Violating Adversarial Perturbations#324843
- AI Safety: Not Optional, Not Later#999906
- BAITBENCH: Measuring Agent Reward Hacking with Optional Shortcuts Planted in ML Tasks#818778
Record · ID 972066
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