A Model Organism for Studying Unverbalized Evaluation Awareness
cs.CL
Submitted: 2026-10-16
Updated: 2026-10-16
Terminology
Sources
- Taken out of context: On measuring situational awareness in LLMs
- Eliciting Secret Knowledge from Language Models
- Models That Know How Evaluations Are Designed Score Safer
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
- Evaluation Awareness in Language Models Has Limited Effect on Behaviour
- Decomposing and Measuring Evaluation Awareness
- Agentic Misalignment: How LLMs Could Be Insider Threats
- Auditing language models for hidden objectives
- Large Language Models Often Know When They Are Being Evaluated
- Stress Testing Deliberative Alignment for Anti-Scheming Training
- AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviors
- Believe It or Not: How Deeply do LLMs Believe Implanted Facts?
- Predicting LLM Safety Before Release by Simulating Deployment
- Instruction-Following Evaluation for Large Language Models
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data