arXiv (All)
open access
Models That Know How Evaluations Are Designed Score Safer
The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings. Prior work has identified test-time contextual cues, such as hypothetical scenarios, as a source of verbalized evaluation awareness and subsequent behavioral shift. In this paper,
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
- Beyond Fluency: A Human-Centered Evaluation Rubric for Grounding, Answerability, and Reliability in LLM Outputs#118367
- Towards interactive evaluations for interaction harms in human-AI systems#1109746
- Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents#422304
- MA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt Optimization#1118430
- Why Safety-First AI Governance Risks Producing Unsafe Systems#692739
Record · ID 984168
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